REVIEW 15 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
MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds
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.
Forward citations
Cited by 15 Pith papers
-
CasaMaestro: Multi-View Panoramas for House-Scale 3D Reconstruction
CasaMaestro predicts metric depth and poses from sparse multi-view panoramas to enable fast house-scale 3D reconstruction.
-
$\pi^3$: Permutation-Equivariant Visual Geometry Learning
π³ is a feed-forward network with full permutation equivariance that outputs affine-invariant poses and scale-invariant local point maps without reference frames, reaching state-of-the-art on camera pose, depth, and d...
-
What VGGT Knows About Overlap: Probing Geometric Foundation Models for Co-Visibility
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.
-
TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction
TriSplat predicts oriented triangle primitives from images in one forward pass to produce simulation-ready 3D meshes with competitive rendering quality.
-
Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective
The paper proposes a problem-driven taxonomy for feed-forward 3D scene modeling that groups methods by five core challenges: feature enhancement, geometry awareness, model efficiency, augmentation strategies, and temp...
-
Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction
Scal3R achieves better accuracy and consistency in large-scale 3D scene reconstruction by maintaining a compressed global context through test-time adaptation of lightweight neural networks on long video sequences.
-
Self-Improving 4D Perception via Self-Distillation
SelfEvo enables pretrained 4D perception models to self-improve on unlabeled videos via self-distillation, delivering up to 36.5% relative gains in video depth estimation and 20.1% in camera estimation across eight be...
-
OVGGT: O(1) Constant-Cost Streaming Visual Geometry Transformer
OVGGT achieves constant O(1) memory and compute for streaming 3D geometry reconstruction by using FFN-residual-based KV cache compression and dynamic anchor protection, matching state-of-the-art accuracy on long sequences.
-
PAGE-4D: Disentangled pose and geometry estimation for vggt-4d perception
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.
-
PAGE-4D: Disentangled pose and geometry estimation for vggt-4d perception
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.
-
OpenM3D: Open Vocabulary Multi-view Indoor 3D Object Detection without Human Annotations
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.
-
VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction
VLM-3R augments VLMs with implicit 3D tokens from monocular video via geometry encoding and 200K+ 3D reconstructive QA pairs, plus a new 138K-pair temporal benchmark, to support spatial and embodied reasoning.
-
Bundle Adjustment in the Eager Mode
Introduces an eager-mode PyTorch BA library with GPU-accelerated sparse ops claiming 18.5-23x speedups over GTSAM, g2o, and Ceres.
-
QVGGT: Post-Training Quantized Visual Geometry Grounded Transformer
QVGGT uses per-block mixed-precision analysis, outlier token filtering with PCA compensation, and task-aware scale search to achieve near-lossless W4A16 quantization of VGGT with 3-4.9x memory savings and 2.8x speedup.
-
FlyMeThrough: Human-AI Collaborative 3D Indoor Mapping with Commodity Drones
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.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.