Pith. sign in

REVIEW 8 cited by

MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds

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 2412.06974 v1 pith:6N5GSPBG submitted 2024-12-09 cs.CV cs.AI

classification cs.CVcs.AI
keywords viewviewsmulti-viewreconstructionmv-dust3rreferenceacrossblocks
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent sparse multi-view scene reconstruction advances like DUSt3R and MASt3R no longer require camera calibration and camera pose estimation. However, they only process a pair of views at a time to infer pixel-aligned pointmaps. When dealing with more than two views, a combinatorial number of error prone pairwise reconstructions are usually followed by an expensive global optimization, which often fails to rectify the pairwise reconstruction errors. To handle more views, reduce errors, and improve inference time, we propose the fast single-stage feed-forward network MV-DUSt3R. At its core are multi-view decoder blocks which exchange information across any number of views while considering one reference view. To make our method robust to reference view selection, we further propose MV-DUSt3R+, which employs cross-reference-view blocks to fuse information across different reference view choices. To further enable novel view synthesis, we extend both by adding and jointly training Gaussian splatting heads. Experiments on multi-view stereo reconstruction, multi-view pose estimation, and novel view synthesis confirm that our methods improve significantly upon prior art. Code will be released.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

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

  1. Rig3R: Rig-Aware Conditioning for Learned 3D Reconstruction

    cs.CV 2025-06 conditional novelty 7.0 of 10

    Rig3R conditions learned 3D reconstruction on optional rig metadata and predicts rig-relative raymaps, enabling state-of-the-art pose estimation and rig calibration discovery from images.

  2. What VGGT Knows About Overlap: Probing Geometric Foundation Models for Co-Visibility

    cs.CV 2026-07 accept novelty 6.5 of 10

    Frozen VGGT layers contain hierarchical co-visibility signals that a <7.5M MoE head extracts to raise Co-VisiON pairwise IoU* by >25% and multiview by ~10% over prior work.

  3. 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.

  4. OpenM3D: Open Vocabulary Multi-view Indoor 3D Object Detection without Human Annotations

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A single-stage image-based detector that, trained with pseudo boxes from SAM segments and CLIP features, detects and classifies arbitrary indoor objects in 3D at 0.3 seconds per scene.

  5. PanSt3R: Multi-view Consistent Panoptic Segmentation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A single network jointly reconstructs 3D scene geometry and predicts multi-view consistent panoptic segmentation from unposed images in one forward pass, without test-time optimization.

  6. UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    Fine-tuning a pretrained video diffusion transformer to predict geometry in one shared global frame produces consistent, camera-free surface normals and coordinates across entire video clips.

  7. X-GRM: Large Gaussian Reconstruction Model for Sparse-view X-rays to Computed Tomography

    eess.IV 2025-05 conditional novelty 6.0 of 10

    A large transformer with fixed-voxel Gaussian splatting reconstructs CT volumes from 6-10 X-ray projections in under a second, substantially beating prior sparse-view methods in simulation.

  8. FlyMeThrough: Human-AI Collaborative 3D Indoor Mapping with Commodity Drones

    cs.HC 2025-08 conditional novelty 5.0 of 10

    A commodity-drone, RGB-only pipeline with human-AI annotation produces 3D indoor maps with localized points of interest, evaluated in 11 of 12 scanned buildings.

Pith tools