arXiv Computer Vision

WHTMix: Efficient Stereo Depth Estimation via Walsh-Hadamard Token Mixing

WHTMix replaces the global self‑attention stage in stereo transformers with a data‑independent Walsh‑Hadamard token mixer, achieving the same end‑point error on synthetic driving data while cutting model compute by 2.46× and single‑image inference latency by 2.65×. The log‑linear cost of the mixer is especially advantageous for high‑resolution stereo matching, as shown by a complexity analysis that links benefits to the ratio of sequence length to channel width. Additionally, a hybrid log‑disparity loss is introduced to up‑weight small‑disparity pixels, improving accuracy on distant objects without extra computational cost.

arXiv Computer Vision

Sep 22

Revisiting Multi-View Stereo: A Sequence-to-Sequence Formulation

The paper proposes a new sequence-to-sequence formulation for multi-view stereo (MVS) that jointly predicts 3D geometry for all input views using a global transformer architecture. It introduces ray‑map embeddings to inject camera parameters into image tokens and a unified global cost volume to capture 3D structure across all views. Experiments on public benchmarks demonstrate state‑of‑the‑art performance, outperforming both traditional MVS and feed‑forward reconstruction baselines.

By Aoxiang Fan, Corentin Dumery, Nicolas Talabot, Pascal Fua

llms rag computer-vision benchmarks

arXiv Computer Vision

Sep 22

VGGT-Prime: Compute-Adaptive Mixture-of-Heads for Efficient Visual Geometry Transformers

arXiv:2609.23733v1 Announce Type: new Abstract: Feed-forward visual geometry models such as the Visual Geometry Grounded Transformer (VGGT) have recently enabled direct 3D reconstruction from multi-v...

By Abteen Arab, Guile Wu, Chengjie Huang, Dongfeng Bai

llms efficiency

arXiv Computer Vision

Aug 25

StereoDiff: Stereo-Diffusion Synergy for Video Depth Estimation

arXiv:2506.20756v4 Announce Type: replace Abstract: Recent video depth estimation methods achieve great performance by following the paradigm of image depth estimation, i.e., typically fine-tuning pr...

By Haodong Li, Chen Wang, Jiahui Lei, Kostas Daniilidis, Lingjie Liu

diffusion computer-vision fine-tuning benchmarks

arXiv Computer Vision

Oct 1

FAST: Flow Any Scene Transformer

arXiv:2609.39748v1 Announce Type: new Abstract: Scaling has become a primary driver of progress in language and vision foundation models, yet its role in precise correspondence matching remains under...

By Yongjian Zhang, Longguang Wang, Zhuo Song, Zhiheng Fu, Liang Lin, Yulan Guo

llms benchmarks

arXiv Computer Vision

Sep 1

PhasorNet: Learning Structure from Frequency for Real-Time Stereo Matching

arXiv:2608.29819v1 Announce Type: new Abstract: Accurate stereo matching remains challenging in ill-posed regions such as fine structures, reflective, or transparent objects, where appearance cues ar...

By Md Raqib Khan, Santosh Kumar Vipparthi, Subrahmanyam Murala

llms benchmarks

arXiv Computer Vision

6d ago

Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer

arXiv:2605.15828v4 Announce Type: replace Abstract: Feed-forward 3D reconstruction models, represented by Visual Geometry Grounded Transformer (VGGT), jointly predict multiple visual geometry tasks s...

By Yipu Zhang, Jintao Cheng, Weilun Feng, Jiehao Luo, Chuanguang Yang, Zhulin An, Yongjun Xu, Wei Zhang

llms computer-vision efficiency benchmarks

Hugging Face Trending Papers

Sep 30

FAST: Flow Any Scene Transformer

Scaling has become a primary driver of progress in language and vision foundation models, yet its role in precise correspondence matching remains underexplored. In this work, we present Flow Any Scene...

llms benchmarks

arXiv AI

Jul 10

LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows

arXiv:2604. 05182v2 Announce Type: replace-cross Abstract: We introduce the Large Sparse Reconstruction Model to study how scaling transformer context windows affects feed-forward 3D reconstruction.

By Zhengqin Li, Cheng Zhang, Jakob Engel, Zhao Dong

llms benchmarks

arXiv Computer Vision

Aug 25

StereoDiffuer: Diffusion-based Progressive Geometry Modeling with Saliency Attention Perception for Stereo Matching

arXiv:2608.21710v1 Announce Type: new Abstract: With the advance of deep neural networks, the quality of disparity maps obtained through stereo matching has steadily improved. However, existing stere...

By Bohan Li

diffusion benchmarks

arXiv Computer Vision

Sep 22

CMAMBADEPTH: Self-supervised Monocular Depth Estimation with Channel Mamba and Hybrid Attention

arXiv:2609.24494v1 Announce Type: new Abstract: Accurate monocular depth estimation serves as a core enabler for single camera scene understanding. However, existing self-supervised monocular depth e...

By Xuezhi Xiang, Jiayao Liu, Heqi Xiang, Yuqi Hu, Yiming Chen, Shanjun Zhang

computer-vision

arXiv Computer Vision

5d ago

MixPT: Point Transformer with Interleaved Window and Global Attention

MixPT is a point transformer that combines window and global attention blocks in an interleaved schedule, using a fixed serialization pattern for window blocks. It applies global attention to spatially pooled tokens for large scenes, feeding residual updates back to the original-resolution stream. Experiments on indoor and outdoor benchmarks show MixPT achieves competitive accuracy with lower latency than existing window- or global-attention baselines, and can scale by repeating the interleaved pattern.

By Minkyun Seo, Hyungtae Lim, Jaesik Park

llms benchmarks

arXiv Machine Learning

Jul 7

SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers

arXiv:2607. 03612v1 Announce Type: cross Abstract: Feed-forward 3D reconstruction (F3R) transformers have recently achieved remarkable success.

By Jianing Deng, Yuanzhe Li, Jialu Wang, Song Wang, Tianlong Chen, Huanrui Yang, Jingtong Hu

llms computer-vision efficiency

Related stories