Pith. sign in

REVIEW 9 cited by

GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors

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 2504.01016 v1 pith:XA5JZEJT submitted 2025-04-01 cs.GR cs.AIcs.CV

classification cs.GRcs.AIcs.CV
keywords pointestimationgeometrycraftervideovideosdiffusionlatentmodel
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Despite remarkable advancements in video depth estimation, existing methods exhibit inherent limitations in achieving geometric fidelity through the affine-invariant predictions, limiting their applicability in reconstruction and other metrically grounded downstream tasks. We propose GeometryCrafter, a novel framework that recovers high-fidelity point map sequences with temporal coherence from open-world videos, enabling accurate 3D/4D reconstruction, camera parameter estimation, and other depth-based applications. At the core of our approach lies a point map Variational Autoencoder (VAE) that learns a latent space agnostic to video latent distributions for effective point map encoding and decoding. Leveraging the VAE, we train a video diffusion model to model the distribution of point map sequences conditioned on the input videos. Extensive evaluations on diverse datasets demonstrate that GeometryCrafter achieves state-of-the-art 3D accuracy, temporal consistency, and generalization capability.

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

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

  1. GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    GenRecon lifts object-level generative priors to scene-scale reconstruction by chunking scenes and using projection-based conditioning on multi-view features, claiming 16% better results than prior methods.

  2. Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    AmbiSuR adds intrinsic photometric disambiguation and a self-indication module to Gaussian Splatting to resolve ambiguities and improve surface reconstruction accuracy.

  3. Pano2World: End-to-End 3D Generation via Unified Multi-View Sequences

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A single indoor panorama is converted end-to-end into an explorable 3D Gaussian scene via joint multi-view panoramic diffusion and a latent feature adapter that bypasses RGB re-encoding.

  4. Pano2World: End-to-End 3D Generation via Unified Multi-View Sequences

    cs.CV 2026-07 unverdicted novelty 6.0 of 10

    Pano2World generates an explorable 3D Gaussian scene directly from a single indoor panorama via coarse proxy rendering, view-aware joint denoising, and a latent feature adapter.

  5. UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    UniVidX unifies diverse video generation tasks into one conditional diffusion model using stochastic condition masking, decoupled gated LoRAs, and cross-modal self-attention.

  6. PAGE-4D: Disentangled pose and geometry estimation for vggt-4d perception

    cs.CV 2025-10 conditional novelty 6.0 of 10

    A fine-tuned VGGT with a learned dynamics mask improves camera pose, depth, and point-cloud reconstruction on dynamic-scene benchmarks over the original static-scene model.

  7. PAGE-4D: Disentangled pose and geometry estimation for vggt-4d perception

    cs.CV 2025-10 unverdicted novelty 6.0 of 10

    PAGE-4D is a feedforward extension of VGGT that uses a dynamics-aware aggregator and mask to disentangle pose estimation from geometry reconstruction in videos with moving objects.

  8. ViPE: Video Pose Engine for 3D Geometric Perception

    cs.CV 2025-08 unverdicted novelty 5.0 of 10

    ViPE estimates camera intrinsics, motion, and dense near-metric depth from uncalibrated videos, outperforming baselines on TUM and KITTI while releasing annotations for 96M frames across real and generated videos.

  9. Reconstructing 4D Spatial Intelligence: A Survey

    cs.CV 2025-07 accept novelty 4.0 of 10

    A review that classifies 4D scene reconstruction methods into five progressive levels: low-level cues, scene components, dynamic scenes, interactions, and physics.

Pith tools