@kwangmoo_yi: Leroy et al., "BLASt3R: Bundle Adjustment of Any Image Set with Multi-View Matching and Monocular Priors" We are back t…
Summary
A research paper on bundle adjustment for any image set using multi-view matching and monocular priors, achieving state-of-the-art results in computer vision.
View Cached Full Text
Cached at: 09/09/26, 03:59 PM
Leroy et al., “BLASt3R: Bundle Adjustment of Any Image Set with Multi-View Matching and Monocular Priors”
We are back to image matching again I guess? Bundle adjusment with coarse/fine matching and depth scaling. State-of-the-art results. https://t.co/f0na1G9SfA
Similar Articles
BA-T: An Iterative Transformer for Two-View Bundle Adjustment
BA-T is an iterative Transformer architecture for two-view bundle adjustment that improves 3D reconstruction accuracy and cross-view consistency using a lightweight design with only 16% of conventional decoder parameters, matching or surpassing larger models.
MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors
MetaView proposes a diffusion-based monocular novel view synthesis framework that combines implicit geometry priors with metric depth guidance to achieve consistent and controllable rendering under large viewpoint changes from a single image.
@ManlingLi_: Planning with the views: Can VLMs predict how each camera move changes the view, and plan many such moves ahead? We int…
Introduces ViewSuite, a benchmark with 6DoF camera control and ~165K tasks for evaluating VLMs' ability to plan camera moves. Finds a planning gap where models can track but not compose plans, and proposes View Graph Distillation (RL-Graph-SFT) to improve success from 2.5% to 47.8%.
Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLM
This paper proposes a query-based cross-modal projector that compresses visual tokens via cross-attention to improve Mamba-based multimodal LLMs, boosting both performance and throughput on vision-language benchmarks while eliminating the need for manual 2D scan order design.
Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching
This paper introduces ReasonMatch-Bench, a benchmark for wide-baseline matching in multimodal LLMs, and proposes Dynamic Correspondence Reinforcement Learning (DCRL) to improve spatial reasoning. Experiments show significant gains on the benchmark while maintaining general performance.