Pith. sign in

REVIEW 10 cited by

Sapiens: Foundation for Human Vision Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2408.12569 v3 pith:QZEFOG4O submitted 2024-08-22 cs.CV

Sapiens: Foundation for Human Vision Models

classification cs.CV
keywords modelssapienstaskshumanhuman-centricacrossdatadepth
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We present Sapiens, a family of models for four fundamental human-centric vision tasks -- 2D pose estimation, body-part segmentation, depth estimation, and surface normal prediction. Our models natively support 1K high-resolution inference and are extremely easy to adapt for individual tasks by simply fine-tuning models pretrained on over 300 million in-the-wild human images. We observe that, given the same computational budget, self-supervised pretraining on a curated dataset of human images significantly boosts the performance for a diverse set of human-centric tasks. The resulting models exhibit remarkable generalization to in-the-wild data, even when labeled data is scarce or entirely synthetic. Our simple model design also brings scalability -- model performance across tasks improves as we scale the number of parameters from 0.3 to 2 billion. Sapiens consistently surpasses existing baselines across various human-centric benchmarks. We achieve significant improvements over the prior state-of-the-art on Humans-5K (pose) by 7.6 mAP, Humans-2K (part-seg) by 17.1 mIoU, Hi4D (depth) by 22.4% relative RMSE, and THuman2 (normal) by 53.5% relative angular error. Project page: https://about.meta.com/realitylabs/codecavatars/sapiens.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. BodyReLux: Temporally Consistent Full-Body Video Relighting

    cs.CV 2026-05 unverdicted novelty 7.0

    BodyReLux achieves photorealistic, temporally consistent full-body video relighting via a diffusion model with token-based lighting conditioning trained on a hybrid static-dynamic capture dataset.

  2. SignMAE: Segmentation-Driven Self-Supervised Learning for Sign Language Recognition

    cs.CV 2026-05 unverdicted novelty 7.0

    SignMAE uses segmentation-driven masking in a mask-and-reconstruct self-supervised task to learn fine-grained sign representations, achieving state-of-the-art accuracy on WLASL, NMFs-CSL, and Slovo with fewer frames a...

  3. InverseDraping: Recovering Sewing Patterns from 3D Garment Surfaces via BoxMesh Bridging

    cs.CV 2026-04 unverdicted novelty 7.0

    A two-stage autoregressive framework centered on BoxMesh recovers parametric sewing patterns from 3D garment surfaces, claiming state-of-the-art results on benchmarks and generalization to real scans and single-view images.

  4. SAM 3: Segment Anything with Concepts

    cs.CV 2025-11 unverdicted novelty 7.0

    SAM 3 introduces promptable concept segmentation that doubles accuracy of prior systems on images and videos while improving standard SAM segmentation performance.

  5. MeshLAM: Feed-Forward One-Shot Animatable Textured Mesh Avatar Reconstruction

    cs.CV 2026-04 unverdicted novelty 6.0

    MeshLAM reconstructs high-fidelity animatable textured mesh head avatars from a single image via a feed-forward dual shape-texture architecture with iterative GRU decoding and reprojection-based guidance.

  6. GeoRelight: Learning Joint Geometrical Relighting and Reconstruction with Flexible Multi-Modal Diffusion Transformers

    cs.CV 2026-04 unverdicted novelty 6.0

    A unified diffusion transformer jointly solves single-image relighting and 3D reconstruction via a new isotropic NDC-Orthographic Depth representation and mixed synthetic/real training.

  7. HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis

    cs.CV 2026-03 unverdicted novelty 6.0

    HVG-3D uses a 3D-aware diffusion architecture with ControlNet to synthesize high-fidelity hand-object interaction videos from 3D control signals, achieving state-of-the-art spatial fidelity and temporal coherence on t...

  8. VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification

    cs.CV 2025-12 unverdicted novelty 6.0

    VHOI densifies sparse trajectories into color-encoded HOI mask sequences and conditions a fine-tuned video diffusion model on them to produce controllable human-object interaction videos, including full navigation sequences.

  9. Flex4DHuman: Flexible Multi-view Video Diffusion for 4D Human Reconstruction

    cs.CV 2026-06 unverdicted novelty 5.0

    A multi-view video diffusion model conditioned on relative camera poses via extended RoPE generates dense synchronized views from sparse inputs for 4D Gaussian splatting reconstruction, claiming SOTA results on human ...

  10. Agentic Pipeline for Self-Synchronized Multiview Joint Angle Monitoring in Uncalibrated Environments

    cs.CV 2026-05 unverdicted novelty 5.0

    An agentic pipeline combines multimodal LLMs for self-synchronization and verification with monocular pose estimation and geometric optimization to achieve 5.97° MAE joint angle monitoring from uncalibrated multi-view...