Pith.

Computer Vision and Pattern Recognition · arXiv:2609.04958 v2 · submitted 4 Sep 2026 · 40 references

MINT: A Unified Model for World-Space Camera and Hand Motion Estimation from Scalable Egocentric Pipeline Supervision

Zijie Zhu, Weiren Cai, Yizhou Wang, Zhenjie Yang, Yide Liu, Jiahao Chen, Guanqi He

The paper says

“Recovering camera and hand motion in world coordinates from egocentric video is a key capability for activity understanding, robot learning, and augmented reality.”

more of the abstract

Existing systems typically decompose this problem into separate stages for camera motion, depth estimation, hand reconstruction, and trajectory refinement, resulting in substantial computational overhead and preventing the joint modeling of camera and hand motion. We introduce MINT (Minting IN-the-Wild Trajectories), a foundation model for world-space hand motion reconstruction from ego-centric RGB video. From a single shared spatiotemporal video representation, MINT jointly predicts the camera trajectory, field of view (FoV), camera-frame hand states, and per-frame hand observability, and then produces world-space hand motion via explicit coordinate transformations. Training such a model at scale is challenging, since paired world-space camera and hand annotations are scarce. We therefore develop an open-source labeling EGOPIPELINE that converts large collections of public egocentric videos into structured camera-and-hand trajectory supervision. MINT is first pretrained on these large-scale pseudo-labels and then fine-tuned on a small set of high-quality camera-and-hand annotations. Across public benchmarks MINT approaches state-of-the-art accuracy without seeing either benchmark in training, reaching 0.945 frame accuracy, 13.646 mm PA-MPJPE-p and 55.058 px EPE-p for camera-frame bimanual reconstruction on HOT3D, 4.690 mm RPE-T and 0.284 degrees RPE-R for camera trajectory, and a 3.67x end-to-end speedup over the labeling pipeline that supervises it. We release the model, training and inference code, labeling pipeline, and a curated 1,021-hour egocentric trajectory dataset.

from the abstract

Pith says

Machine review · deepseek-v4-flash · 9 Sep 2026 · what was read was not recorded · not checked by a person

It can be wrong. Challenge this review or reply to it.

The passes disagreed. Reader: holds up. Skeptic: holds up only with conditions. Referee: major revision.

Solid engineering on a useful problem, but the central zero-shot claim has a blind spot the paper doesn't address. This line is wrong

2 major objections · 6 minor

How often objections from reviews like this one are right: not yet measured

Are you an author? What you can do.

Not checked: figures, code, what the 40 references say.

The paper says, at Section III, Section V.A, and the zero-shot claim throughout

The review did not quote this passage.

Pith says: Objection 1 of 2 · major

The zero-shot evaluation on HOT3D and ARCTIC is central to the paper's claims. However, EgoPipeline includes HaWoR (ref. [39]), which is used to generate the hand pseudo-labels for MINT's stage 1 pretraining. The paper does not disclose whether HaWoR was trained on HOT3D or ARCTIC.

more of objection 1

If HaWoR has seen these benchmarks, then the pseudo-labels carry information from them, compromising the zero-shot nature of MINT's evaluation. This is a load-bearing issue; the authors must either provide evidence that HaWoR's training data does not include HOT3D/ARCTIC, or perform an ablation that removes HaWoR from the pipeline to assess the impact on generalization, and adjust the zero-shot claim accordingly. Without this verification, the headline claim of 'zero-shot competitive accuracy' is unsupported.

The paper says, at Section III and Section V.A

The review did not quote this passage.

Pith says: Objection 2 of 2 · major

The quality of the pseudo-labels from EgoPipeline is not independently verified beyond downstream task performance. While the final results suggest the labels are useful, error propagation from the multiple models (YOLO, GeoCalib, MoGe-2, MegaSaM, HaWoR) could affect the reliability of the supervision, especially for the camera trajectory (scale drift).

more of objection 2

The paper acknowledges scale drift but does not quantify the error distribution in the pseudo-labels. The authors should provide a direct comparison of a subset of pseudo-labels against ground-truth annotations (e.g., on a held-out portion of the in-house corpus) to demonstrate their suitability for pretraining.

6 minor objections

The paper says, at Abstract and Table 2

Pith says: minor objection 1 of 6

The abstract reports RPE-T as 4.690 mm on HOT3D, while Table 2 shows 4.694 mm (mean). Please ensure consistency.

The paper says, at Table 5

Pith says: minor objection 2 of 6

The speedup factor for HaWoR is listed as 12.0× on one GPU (from 105.1 ms to 72.4 ms gives 1.45×, not 12.0×). Verify the calculation; the factor appears to be relative to VITRA, but the row labels are ambiguous. Clarify the reference for each speedup column.

show 4 more

The paper says, at Section IV-C, Eq. (5)

Pith says: minor objection 3 of 6

The notation ω̃ uses ω in the denominator; please ensure that the norm is non-zero (add a small epsilon for numerical stability).

The paper says, at Section V-D, Table 4

Pith says: minor objection 4 of 6

The 'Full mixture' row also includes EPIC-KITCHENS and the in-house corpus, but the table caption says 'only the source composition changes' – clarify that the mixture adds more sources beyond Ego4D and EgoDex.

The paper says, at Conclusion

Pith says: minor objection 5 of 6

The limitations mention scale drift from monocular reconstruction, which is appropriate. Consider also noting that the in-house camera-trajectory corpus used in stage 2 is not publicly released, which may limit reproducibility.

The paper says, at Figure 2

Pith says: minor objection 6 of 6

The pipeline diagram uses 'MegaSam' but the text uses 'MegaSaM'; please standardize the capitalization.

What would settle it

Check the published training data of HaWoR (reference [39]) to see if HOT3D or ARCTIC appear. If either benchmark is included in HaWoR's training, then MINT's zero-shot evaluation is compromised. If not, the concern is mitigated but should still be documented.

from the skeptic's reading

How the review went

4 readings by deepseek-v4-flash · 9 Sep 2026

  1. Reader holds up confidence high
  2. Skeptic disagrees: says it holds up only with conditions 25 s · 15,399 tokens read, 2,583 written Zero-shot claim may be compromised if pipeline component HaWoR was trained on the evaluation benchmarks; this potential data leakage is not addressed.
  3. Editor wrote the verdict above 12 s · 16,163 tokens read, 1,123 written
  4. Referee major revision: 2 major objections, 6 minor 19 s · 15,653 tokens read, 1,921 written

Not run on this paper: the simulated authors' defence.

Pith did not check this review's objections against the paper.

The review in full

The review in brief, machine-written

The paper builds a unified feed-forward model for world-space hand and camera motion from egocentric video. That's a real engineering advance: a single pass replaces a cascade of separate models, and the speedup is genuine. The two-stage training scheme—pretrain on pipeline pseudo-labels, then fine-tune a small high-quality set—is sensible, and the ablation on the data mixture shows the value of diversity. The authors also release code, model, and a 1021-hour trajectory dataset, which is a service to the field.

Now the soft spot. The paper hangs its hat on being zero-shot on HOT3D and ARCTIC. But the pretraining pseudo-labels are generated by a pipeline that includes HaWoR (a hand reconstruction model whose training data is not disclosed). If HaWoR saw either benchmark during its own training, then information from those benchmarks leaked into MINT's pretraining through the pseudo-labels. This would make the 'zero-shot' claim misleading. The paper never discusses this, never checks HaWoR's training data, and never runs a control experiment (e.g., ablating HaWoR's influence or verifying that MINT's outputs are not correlated with benchmark-specific properties). The stress-test note on this point is correct and load-bearing.

I don't think the authors are being dishonest—this is a common oversight in the cascade-training literature. But for a paper that markets zero-shot generalization as a headline result, this is a real omission. The main experiments showing competitive numbers could partly reflect benchmark leakage rather than true generalization.

Other soft spots: the camera trajectory stage-2 correction overshoots on ARCTIC (arc-length ratio 1.412), and the 32-frame window leaves long-range drift unaddressed. These are acknowledged limitations.

Who this is for: anyone working on egocentric hand tracking, embodied AI training, or AR perception. The engineering is solid, and the released pipeline and data are useful even if the zero-shot claim needs qualification.

Recommendation: I'd send this to peer review, but only with a strong request that the authors either verify the training data of all pipeline components or run a clean ablation that rules out benchmark leakage. If they can do that, the paper is a solid accept. If they can't, the zero-shot narrative is weakened considerably and the paper becomes a less striking contribution.

The strongest objection

The paper emphasizes that MINT is evaluated zero-shot on HOT3D and ARCTIC, with no benchmark data seen in training. However, the EgoPipeline used to generate stage-1 pseudo-labels includes HaWoR (Sec. III), a hand reconstruction model whose training data is not disclosed. If HaWoR was trained on HOT3D or ARCTIC (common in the field), then the pseudo-labels would encode information from those benchmarks, leaking into MINT's pretraining. This would invalidate the zero-shot claim, which is central to the paper's argument for generalization. The paper does not verify the training data of any pipeline component, and the 'zero-shot' assertion rests on this unchecked assumption. This is a load-bearing concern because the headline results (zero-shot competitive accuracy) would be weakened if leakage is confirmed.

The reader's weakest assumption focused on pseudo-label accuracy, which the paper partially addresses through Stage 2 and ablations. My concern is about data leakage: the zero-shot evaluation regime may be contaminated by HaWoR's potential training on the same benchmarks. This is a different and more fundamental issue, as it directly affects the validity of the main experimental claim. The paper does not discuss this, making it a gap that should be resolved. A conditional verdict is appropriate: accept only if the authors can demonstrate that no pipeline component was trained on the evaluation domains, or if retraining MINT with leakage-free labels reproduces the results. If leakage is confirmed, the central contribution weakens significantly.

The referee's report

If the zero-shot claim holds, MINT represents a significant advance in unifying camera and hand motion estimation from egocentric video, removing the need for separate detectors, motion infillers, and test-time optimization. The release of the model, code, pipeline, and a large curated trajectory dataset (1,021 hours) is a valuable resource for the community. The speedup (3.67× over EgoPipeline) and the demonstration that pseudo-labels from public video can suffice for pretraining are practically important.

Pith's reading of the paper (a machine's summary, not the authors')

MINT claims that a single feed-forward network can recover, from egocentric RGB video, the camera trajectory, field of view, both hands' MANO states, and per-frame hand visibility, then map the hand states into world coordinates through a differentiable transform. To train it at scale without paired world-space annotations, the paper builds a labeling pipeline that converts 1,021 hours of public egocentric video into camera-and-hand trajectory pseudo-labels, then fine-tunes only the camera head on a small high-precision dataset to correct metric scale. On HOT3D and ARCTIC, both unseen in training, MINT approaches or beats single-task state-of-the-art baselines and achieves a 3.67x end-to-end speedup over the labeling pipeline that produced its supervision. The paper's thesis is that automatically reconstructed motion supervision from ordinary video is sufficient to learn generalizable world-space egocentric motion reconstruction.

What carries the argument. The load-bearing object is a geometric context transformer (GCT) taken from long-range 3D reconstruction pretraining, which encodes each 32-frame window by alternating frame attention for spatial structure and global attention for temporal geometric context, so egomotion is inferred from cross-frame evidence rather than single-frame cues. On that shared representation sit four prediction heads: camera extrinsics with iterative pose refinement, field of view predicted from the camera token, MANO parameters for both hands decoded through per-hand queries with refinement iterations, and a lightweight hand-observability head whose probabilities gate whether each hand contributes to the reconstruction and world-frame losses. The argument closes through the differentiable world-frame transformation $p^w_{t,s} = R_t^\top(p^c_{t,s} - t_t)$ and $Q^w_{t,s} = R_t^\top Q^c_{t,s}$, which lets the world-frame loss jointly constrain camera and hand predictions. Training proceeds in two stages: first, coupled camera-hand geometry is learned from the large-scale pseudo-labels; second, with the backbone, hand, observability, and field-of-view modules frozen, only the camera head is adapted on high-precision trajectories to correct the scale ambiguity inherited from monocular reconstruction.

Core claim. The central claim is that world-space camera and bimanual hand motion can be estimated jointly from a shared spatiotemporal geometric representation, in one encoder forward pass per 32-frame window, with no hand detector, motion infiller, test-time optimization, or dense depth intermediate. The paper demonstrates this with MINT, which reuses a pretrained geometric context transformer that alternates frame-level and global attention, and reads four heads from the same features: camera extrinsics, horizontal and vertical field of view, bimanual MANO parameters, and hand observability. The hand states are predicted in camera coordinates and mapped to the world frame through the predicted camera pose via a differentiable transformation, so the world-frame loss explicitly couples camera and hand geometry. No hand label in the training data is human-annotated: stage 1 trains on the pseudo-labels, and stage 2 freezes everything except the camera head and adapts it to a small in-house corpus with device-captured trajectories. The paper reports zero-shot results on HOT3D and ARCTIC, reaching for example 0.945 frame accuracy and 13.646 mm PA-MPJPE-p on HOT3D and the lowest relative translation error on ARCTIC, while improving end-to-end speed 3.67x over the labeling pipeline.

The premise it rests on. The method depends on pseudo-labels produced by a cascade of separately trained models — hand detection, camera calibration, monocular depth, SLAM, and hand reconstruction — whose combined errors are never verified against ground truth, so the whole approach works only if that automatic supervision is accurate enough to teach camera-hand geometry.

If the paper is right (Pith's inferences, not the authors')

Egocentric motion supervision can be produced at scale from ordinary public video via an open-source labeling pipeline, replacing specialized multi-camera or marker-based capture for training data.

Inference becomes a single forward pass per 32-frame sliding window, chained across arbitrary-length videos, so long recordings can be processed at approximately linear cost without detectors or test-time optimization.

Zero-shot performance on unseen benchmarks indicates the learned geometric representation transfers across viewpoints, intrinsics, and interaction styles, allowing new egocentric corpora to be labeled without retraining.

The explicit hand-observability head gates unreliable frames during both training and downstream use, reducing the influence of occlusion and image-boundary truncation on reconstruction quality.

Independent overlapping windows can be processed in parallel across GPUs, yielding a 3.67x end-to-end speedup over the labeling pipeline that generated the training supervision.

The same recipe of a geometry-pretrained feed-forward backbone, pseudo-labeled internet-scale video for supervision, and a small high-accuracy dataset for metric correction could extend to other world-grounded quantities such as body motion, object trajectories, or hand-object contact, wherever paired world-space labels are scarce.

The hand-observability head, trained to predict which frames are geometrically reliable, could double as an uncertainty signal for downstream robot-learning or augmented-reality systems, though the paper does not evaluate it in that role.

The reported ARCTIC arc-length overshoot of 1.412 after scale correction suggests the stage-2 fix trades under-scaling for over-scaling on some domains; conditioning scale correction on scene or motion content, or adding global alignment, is a natural extension.

Because the training labels come from a cascade of independently trained models, MINT's accuracy ceiling is tied to that cascade's joint error; weighting supervision by the pipeline's per-frame confidence instead of hard labels is a testable refinement.

Check this review

Pith stored no record of this review's passes and took no fingerprint of it. Reviews made by code from 13 Nov 2026 on carry both.

How often reviews like this one are right

Reviews like this one: written by deepseek-v4-flash, where what was read was not recorded.

How often objections from reviews like this one are right: not yet measured

Every value above, in the review's public record (JSON)

Reviews by people

This review was written by a machine. No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.

Request a human review

How Pith checks papers · The full audit of this paper · Review history (2 versions)

The paper

Abstract

Recovering camera and hand motion in world coordinates from egocentric video is a key capability for activity understanding, robot learning, and augmented reality. Existing systems typically decompose this problem into separate stages for camera motion, depth estimation, hand reconstruction, and trajectory refinement, resulting in substantial computational overhead and preventing the joint modeling of camera and hand motion. We introduce MINT (Minting IN-the-Wild Trajectories), a foundation model for world-space hand motion reconstruction from ego-centric RGB video. From a single shared spatiotemporal video representation, MINT jointly predicts the camera trajectory, field of view (FoV), camera-frame hand states, and per-frame hand observability, and then produces world-space hand motion via explicit coordinate transformations. Training such a model at scale is challenging, since paired world-space camera and hand annotations are scarce. We therefore develop an open-source labeling EGOPIPELINE that converts large collections of public egocentric videos into structured camera-and-hand trajectory supervision. MINT is first pretrained on these large-scale pseudo-labels and then fine-tuned on a small set of high-quality camera-and-hand annotations. Across public benchmarks MINT approaches state-of-the-art accuracy without seeing either benchmark in training, reaching 0.945 frame accuracy, 13.646 mm PA-MPJPE-p and 55.058 px EPE-p for camera-frame bimanual reconstruction on HOT3D, 4.690 mm RPE-T and 0.284 degrees RPE-R for camera trajectory, and a 3.67x end-to-end speedup over the labeling pipeline that supervises it. We release the model, training and inference code, labeling pipeline, and a curated 1,021-hour egocentric trajectory dataset.

The paper's own sentences, arranged, kept beside the review and separate from it. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.

abstract compiled · 2026-09-23

The authors' main claim, as the classifier picked it out 0.99

“Across public benchmarks MINT approaches state-of-the-art accuracy without seeing either benchmark in training, reaching 0.945 frame accuracy, 13.646 mm PA-MPJPE-p and 55.058 px EPE-p for camera-frame bimanual reconstruction on HOT3D, 4.690 mm RPE-T and 0.284 degrees RPE-R for camera trajectory, and a 3.67x end-to-end speedup over the labeling pipeline that supervises it.”

How the main claim is stated: asserted 1.00

What the abstract itself states, as probabilities: claims first 0.11 · states limitation 0.59 · human participants 0.31 · controlled comparison 0.62 · randomized assignment 0.01 · states quantitative result 0.99 · compares with prior results 0.92 · mentions code or data availability 0.99

The abstract, sentence by sentence

This table labels the abstract only (arXiv listing abstract v2). The number is the probability the classifier gave the label.

SentenceRoleThe authors' own workStates the main conclusionStrength
Recovering camera and hand motion in world coordinates from egocentric video is a key capability for activity understanding, robot learning, and augmented reality. background 1.00 0.05 0.04 asserted 1.00
Existing systems typically decompose this problem into separate stages for camera motion, depth estimation, hand reconstruction, and trajectory refinement, resulting in substantial computational overhead and preventing the joint modeling of camera and hand motion. gap 0.72 0.06 0.03 asserted 1.00
We introduce MINT (Minting IN-the-Wild Trajectories), a foundation model for world-space hand motion reconstruction from ego-centric RGB video. contribution 0.99 0.88 0.12 asserted 1.00
From a single shared spatiotemporal video representation, MINT jointly predicts the camera trajectory, field of view (FoV), camera-frame hand states, and per-frame hand observability, and then produces world-space hand motion via explicit coordinate transformations. method 0.96 0.92 0.16 asserted 1.00
Training such a model at scale is challenging, since paired world-space camera and hand annotations are scarce. gap 0.61 0.22 0.02 asserted 1.00
We therefore develop an open-source labeling EGOPIPELINE that converts large collections of public egocentric videos into structured camera-and-hand trajectory supervision. method 0.82 0.96 0.03 asserted 1.00
MINT is first pretrained on these large-scale pseudo-labels and then fine-tuned on a small set of high-quality camera-and-hand annotations. method 0.99 0.94 0.05 asserted 1.00
Across public benchmarks MINT approaches state-of-the-art accuracy without seeing either benchmark in training, reaching 0.945 frame accuracy, 13.646 mm PA-MPJPE-p and 55.058 px EPE-p for camera-frame bimanual reconstruction on HOT3D, 4.690 mm RPE-T and 0.284 degrees RPE-R for camera trajectory, and a 3.67x end-to-end speedup over the labeling pipeline that supervises it. result 1.00 0.96 0.61 asserted 1.00
We release the model, training and inference code, labeling pipeline, and a curated 1,021-hour egocentric trajectory dataset. contribution 1.00 0.95 0.07 asserted 0.99

What kind of paper the classifier reports this is: method or tool 1.00 · evidence from observation or experiment 0.95

What was examined, and what was not

Sources read

  • arXiv listing abstract v2

Not examined

  • full text
  • figures and tables
  • references and citing sentences
  • relations to other papers

Levels run

  • P abstract

Not run

  • S sections
  • T body sentences
  • C citations
  • R cross-paper relations

How the labels were made

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-09-23: 1 request, 7,203 input tokens.

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON

Figures (3)
Figure 1 of the paper
Figure 1. MINT converts ordinary egocentric video into world-space motion supervision, and MINT recovers that motion in a single forward pass.
Figure 2 of the paper
Figure 2. Overview of EGOPIPELINE. Egocentric videos are first pre-filtered by hand detection. The retained clips are then processed by GeoCalib for camera intrinsics, MoGe-2 for monocular depth, MegaSaM for camera pose, and HaWoR for bimanual hand reconstruction. A final post-processing stage stabilizes the recovered trajectories and composes the camera-frame hand states with the camera trajectory to produce world-space bimanual motion supervision. its device trajectory. These methods show that world-space motion is directly learnable, but they either take the camera trajectory as an input…
Figure 3 of the paper
Figure 3. Architecture of MINT. Each window of 32 egocentric frames is encoded at 378 × 518 by a DINOv2 ViT-L/14 patch embedding, and the resulting frame tokens are processed by the spatiotemporal geometric aggregator of GCT, which alternates frame attention and global attention so that every frame of the window is encoded with bidirectional temporal context. The unified visual-geometric features carry camera, register, scale, and patch tokens, and feed four prediction heads for camera extrinsics, field of view, bimanual MANO parameters, and hand observability. Composing the predicted camera…

Figures are the authors', reproduced from the paper.

References (40)
  1. [39] Jinglei Zhang, Jiankang Deng, Chao Ma, and Rolandos Alexandros Potamias. Hawor: World-space hand motion reconstruction from egocentric videos. In 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 1805–1815, 2025 on Pith
  2. [1] Prithviraj Banerjee, Sindi Shkodrani, Pierre Moulon, et al. Hot3d: Hand and object tracking in 3d from egocentric multi-view videos. In 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 7061–7071, 2025 on Pith
  3. [2] Yu-Wei Chao, Wei Y ang, Yu Xiang, et al. Dexycb: A benchmark for capturing hand grasping of objects. In 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 9040–9049, 2021 on Pith
  4. [3] Lin-Zhuo Chen, Jian Gao, Yihang Chen, et al. Geometric con- text transformer for streaming 3d reconstruction. arXiv preprint arXiv:2604.14141, 2026 on PithPith's reviewarXiv
  5. [4] Dima Damen, Hazel Doughty, Giovanni Maria Farinella, et al. Scaling egocentric vision: the dataset. In European conference on computer vision, pages 753–771, 2018 on Pith
  6. [5] Haoye Dong, Aviral Chharia, Wenbo Gou, Francisco Vicente Car- rasco, and Fernando De la Torre. Hamba: Single-view 3d hand reconstruction with graph-guided bi-scanning mamba. arXiv preprint arXiv:2407.09646, 2024 on PitharXiv
  7. [6] Enes Duran, Muhammed Kocabas, Vasileios Choutas, Zicong Fan, and Michael J Black. Hmp: Hand motion priors for pose and shape estimation from video. In 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (W ACV), pages 6341–6351, 2024 on Pith
  8. [7] Zicong Fan, Omid Taheri, Dimitrios Tzionas, Muhammed Kocabas, Manuel Kaufmann, Michael J Black, and Otmar Hilliges. ARCTIC: A dataset for dexterous bimanual hand-object manipulation. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 12943–12954, 2023 on Pith
  9. [8] Kristen Grauman, Andrew Westbury, Eugene Byrne, et al. Ego4d: Around the world in 3,000 hours of egocentric video. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 18995–19012, 2022 on Pith
  10. [9] Kristen Grauman, Andrew Westbury, Lorenzo Torresani, et al. Ego- exo4d: Understanding skilled human activity from first-and third- person perspectives. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 19383–19400, 2024 on Pith
  11. [10] Ryan Hoque, Peide Huang, David Y oon, et al. Egodex: Learning dexterous manipulation from large-scale egocentric video. In Inter- national Conference on Learning Representations, pages 4218–4237, 2026 on Pith
  12. [11] Simar Kareer, Dhruv Patel, Ryan Punamiya, Pranay Mathur, Shuo Cheng, Chen Wang, Judy Hoffman, and Danfei Xu. Egomimic: Scaling imitation learning via egocentric video. In 2025 IEEE International Conference on Robotics and Automation (ICRA), pages 13226–13233, 2025 on Pith
  13. [12] Vincent Leroy, Y ohann Cabon, and Jérôme Revaud. Grounding image matching in 3d with mast3r. In European conference on computer vision, pages 71–91, 2024 on Pith
  14. [13] Zhengqi Li, Richard Tucker, Forrester Cole, Qianqian Wang, Linyi Jin, Vickie Y e, Angjoo Kanazawa, Aleksander Holynski, and Noah Snavely. Megasam: Accurate, fast, and robust structure and motion from casual dynamic videos. In 2025 IEEE/CVF Conference on Computer Vision and Pat... on Pith
  15. [14] Qixiu Li, Yu Deng, Y aobo Liang, et al. Scalable vision-language- action model pretraining for robotic manipulation with real-life human activity videos. arXiv preprint arXiv:2510.21571, 2025 on PitharXiv
  16. [15] Dixuan Lin, Yuxiang Zhang, Mengcheng Li, Wei Jing, Qi Y an, Qianying Wang, Y ebin Liu, and Hongwen Zhang. Omnihands: Towards robust 4d hand mesh recovery via a versatile transformer. arXiv preprint arXiv:2405.20330, 2024 on PithPith's reviewarXiv
  17. [16] Gyeongsik Moon. Bringing inputs to shared domains for 3D interacting hands recovery in the wild. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 17028– 17037, 2023 on Pith
  18. [17] Maxime Oquab, Timothée Darcet, Théo Moutakanni, et al. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193, 2023 on PithPith's reviewarXiv
  19. [18] Georgios Pavlakos, Dandan Shan, Ilija Radosavovic, Angjoo Kanazawa, David Fouhey, and Jitendra Malik. Reconstructing hands in 3d with transformers. In 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 9826–9836, 2024 on Pith
  20. [19] Rolandos Alexandros Potamias, Jinglei Zhang, Jiankang Deng, and Stefanos Zafeiriou. Wilor: End-to-end 3d hand localization and recon- struction in-the-wild. In 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 12242–12254, 2025 on Pith
show 20 more
  1. [20] Aditya Prakash, Ruisen Tu, Matthew Chang, and Saurabh Gupta. 3d hand pose estimation in everyday egocentric images. In European Conference on Computer Vision, pages 183–202, 2024 on Pith
  2. [21] Javier Romero, Dimitrios Tzionas, and Michael J Black. Embodied hands: Modeling and capturing hands and bodies together. arXiv preprint arXiv:2201.02610, 2022 on PithPith's reviewarXiv
  3. [22] Zehong Shen, Huaijin Pi, Y an Xia, Zhi Cen, Sida Peng, Zechen Hu, Hujun Bao, Ruizhen Hu, and Xiaowei Zhou. World-grounded human motion recovery via gravity-view coordinates. In SIGGRAPH Asia 2024 Conference Papers, pages 1–11, 2024 on Pith
  4. [23] Soyong Shin, Juyong Kim, Eni Halilaj, and Michael J Black. Wham: Reconstructing world-grounded humans with accurate 3d motion. In 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 2070–2080, 2024 on Pith
  5. [24] Zachary Teed and Jia Deng. Droid-slam: Deep visual slam for monocular, stereo, and rgb-d cameras. Advances in neural information processing systems, 34:16558–16569, 2021 on Pith
  6. [25] Eugene Valassakis and Guillermo Garcia-Hernando. Handdgp: Camera-space hand mesh prediction with differentiable global posi- tioning. In European Conference on Computer Vision, pages 479–496, 2024 on Pith
  7. [26] Alexander Veicht, Paul-Edouard Sarlin, Philipp Lindenberger, and Marc Pollefeys. Geocalib: Learning single-image calibration with geometric optimization. In European Conference on Computer Vision, pages 1–20, 2024 on Pith
  8. [27] Shuzhe Wang, Vincent Leroy, Y ohann Cabon, Boris Chidlovskii, and Jerome Revaud. Dust3r: Geometric 3d vision made easy. In 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 20697–20709, 2024 on Pith
  9. [28] Yufu Wang, Ziyun Wang, Lingjie Liu, and Kostas Daniilidis. Tram: Global trajectory and motion of 3d humans from in-the-wild videos. In European Conference on Computer Vision, pages 467–487, 2024 on Pith
  10. [29] Qianqian Wang, Yifei Zhang, Aleksander Holynski, Alexei A Efros, and Angjoo Kanazawa. Continuous 3d perception model with persistent state. In 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 10510–10522, 2025 on Pith
  11. [30] Ruicheng Wang, Sicheng Xu, Yue Dong, Yu Deng, Jianfeng Xiang, Zelong Lv, Guangzhong Sun, Xin Tong, and Jiaolong Y ang. Moge- 2: Accurate monocular geometry with metric scale and sharp details. Advances in Neural Information Processing Systems, 38:35928–35959, 2026 on Pith
  12. [31] Yifan Wang, Jianjun Zhou, Haoyi Zhu, Wenzheng Chang, Y ang Zhou, Zizun Li, Junyi Chen, Jiangmiao Pang, Chunhua Shen, and Tong He. π3: Permutation-Equivariant Visual Geometry Learning. In International Conference on Learning Representations, pages 10481– 10497, 2026 on Pith
  13. [32] Jianyuan Wang, Minghao Chen, Nikita Karaev, Andrea Vedaldi, Christian Rupprecht, and David Novotny. V ggt: Visual geometry grounded transformer. In 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 5294–5306, 2025 on Pith
  14. [33] Yuxi Wang, Chengkai Jin, Yufei Liu, Wenqi Ouyang, Tianyi Wei, Zhiwei Zeng, Siyuan Huang, Zhiqi Shen, and Xingang Pan. The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction. arXiv preprint arXiv:2606.30308, 2026 on PithPith's reviewarXiv
  15. [34] Vickie Y e, Georgios Pavlakos, Jitendra Malik, and Angjoo Kanazawa. Decoupling human and camera motion from videos in the wild. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 21222–21232, 2023 on Pith
  16. [35] Brent Yi, Vickie Y e, Maya Zheng, Yunqi Li, Lea Müller, Georgios Pavlakos, Yi Ma, Jitendra Malik, and Angjoo Kanazawa. Estimating body and hand motion in an ego-sensed world. In 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 7072–7084, 2025 on Pith
  17. [36] Wei Yin, Chi Zhang, Hao Chen, Zhipeng Cai, Gang Yu, Kaixuan Wang, Xiaozhi Chen, and Chunhua Shen. Metric3d: Towards zero- shot metric 3d prediction from a single image. In 2023 IEEE/CVF International Conference on Computer Vision (ICCV), pages 9009– 9019, 2023 on Pith
  18. [37] Zhengdi Yu, Stefanos Zafeiriou, and Tolga Birdal. Dyn-hamr: Recov- ering 4d interacting hand motion from a dynamic camera. In 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 27716–27726, 2025 on Pith
  19. [38] Shuai Yuan, Y antai Y ang, Xiaotian Y ang, Xupeng Zhang, Zhonghao Zhao, Lingming Zhang, and Zhipeng Zhang. Infinitevggt: Visual geometry grounded transformer for endless streams. arXiv preprint arXiv:2601.02281, 2026 on PitharXiv
  20. [40] Junyi Zhang, Charles Herrmann, Junhwa Hur, et al. Monst3r: A simple approach for estimating geometry in the presence of motion. In International Conference on Learning Representations, pages 82863– 82886, 2025 on Pith
Cited by 8 Pith papers

Challenges and discussion

Disagree with the review, or know something it missed? Leave a comment, or challenge this review formally: a challenge becomes a permanent entry in this paper's record, and its decision is published here.

No comments yet.

Sign in to comment