Pith. sign in

REVIEW 8 cited by

MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2401.11673 v1 pith:KN3Y5YGR submitted 2024-01-22 cs.CV

MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo

Chenjie Cao , Xinlin Ren , Yanwei Fu This is my paper
classification cs.CV
keywords attentionmvsformerdetailsdifferentfeaturemechanismsmethodmodules
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Recent advancements in learning-based Multi-View Stereo (MVS) methods have prominently featured transformer-based models with attention mechanisms. However, existing approaches have not thoroughly investigated the profound influence of transformers on different MVS modules, resulting in limited depth estimation capabilities. In this paper, we introduce MVSFormer++, a method that prudently maximizes the inherent characteristics of attention to enhance various components of the MVS pipeline. Formally, our approach involves infusing cross-view information into the pre-trained DINOv2 model to facilitate MVS learning. Furthermore, we employ different attention mechanisms for the feature encoder and cost volume regularization, focusing on feature and spatial aggregations respectively. Additionally, we uncover that some design details would substantially impact the performance of transformer modules in MVS, including normalized 3D positional encoding, adaptive attention scaling, and the position of layer normalization. Comprehensive experiments on DTU, Tanks-and-Temples, BlendedMVS, and ETH3D validate the effectiveness of the proposed method. Notably, MVSFormer++ achieves state-of-the-art performance on the challenging DTU and Tanks-and-Temples benchmarks.

discussion (0)

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

Forward citations

Cited by 8 Pith papers

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

  1. PAGaS: Pixel-Aligned 1DoF Gaussian Splatting for Depth Refinement

    cs.CV 2026-04 unverdicted novelty 7.0

    PAGaS refines multi-view stereo depths by optimizing 1DoF Gaussians whose positions and sizes are fixed by back-projected pixel volumes, producing detailed depth maps that outperform reference baselines on 3D reconstr...

  2. 3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement

    cs.CV 2026-06 conditional novelty 6.0

    A training-free 3D scene-adaptive human animation framework that controls human motion and camera trajectories via ground-adaptive retargeting and visibility-masked point-cloud fusion in a diffusion backbone.

  3. 3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement

    cs.CV 2026-06 unverdicted novelty 6.0

    Presents a scene-adaptive 3D human animation method using ground-adaptive motion retargeting and viewpoint-adaptive latent fusion to control human trajectories and camera views, reporting gains on two benchmarks.

  4. GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction

    cs.CV 2026-05 unverdicted novelty 6.0

    GeoQuery replaces corrupted rendering features with geometry-aligned proxy queries and restricts cross-view attention to local windows, enabling robust diffusion-based refinement under extreme view sparsity.

  5. SimpleProc: Fully Procedural Synthetic Data from Simple Rules for Multi-View Stereo

    cs.CV 2026-04 unverdicted novelty 6.0

    Procedural rules with NURBS generate MVS training data that outperforms same-scale manual curation and matches or exceeds larger manual datasets.

  6. From Orbit to Ground: Generative City Photogrammetry from Extreme Off-Nadir Satellite Images

    cs.CV 2025-12 unverdicted novelty 6.0

    A technique reconstructs large urban areas from sparse extreme off-nadir satellite images by modeling geometry as a Z-monotonic 2.5D height map SDF and applying a generative network to restore plausible textures on th...

  7. 2K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Prediction

    cs.CV 2026-03 conditional novelty 5.5

    Entropy-guided sparse refinement upgrades frozen low-resolution geometric foundation models to accurate 2K depth and pointmap outputs at a fraction of full-resolution cost.

  8. 3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement

    cs.CV 2026-06 unverdicted novelty 5.0

    Presents a scene-adaptive 3D human image animation framework using ground-adaptive motion retargeting and viewpoint-adaptive latent fusion to control human and camera trajectories, claiming improvements on two benchmarks.