arXiv Computer Vision
CoTL: Compact Token Learning for 3D Scene Representation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Oct 8
S2Tok: Streaming 3D Gaussian Reconstruction with Persistent Spatial Tokens
arXiv:2610.08978v1 Announce Type: new Abstract: Streaming 3D reconstruction requires more than a sequence of geometric predictions: it requires a persistent scene state that can incorporate new evide...
arXiv Computer Vision
Aug 27
Compact Feed-Forward 3D Gaussians via Saliency-Guided Primitive Merging
The paper introduces a structure‑aware merging pipeline that consolidates per‑pixel 3D Gaussian primitives from any feed‑forward reconstruction method into a compact, content‑adaptive Gaussian set. By grouping spatially coherent Gaussians with adaptive superpixel segmentation guided by a saliency map, compressing clusters via a learned encoder, and merging representations across views using geometric overlap and feature similarity, the method reduces the number of Gaussians to about one‑twentieth of the original while preserving visual quality. A level‑of‑detail decoder allows controllable resolution, and the pipeline operates as a backbone‑agnostic post‑processing module, improving robustness and rendering efficiency.
arXiv AI
Sep 10
UniQueR: Unified Query-based Feedforward 3D Reconstruction
UniQueR is a unified query‑based feedforward framework that reconstructs 3D scenes from unposed images by treating reconstruction as a sparse 3D query inference problem. It learns a compact set of 3D anchor points that serve as explicit geometric queries, allowing the network to infer scene structure—including occluded geometry—in a single forward pass. By encoding spatial and appearance priors directly in global 3D space and using a decoupled cross‑attention design, UniQueR achieves strong geometric expressiveness while reducing memory and computational cost, outperforming state‑of‑the‑art feedforward methods on Mip‑NeRF 360 and VR‑NeRF with far fewer primitives.
arXiv Computer Vision
Oct 7
DensiTok: Making Feed-Forward 3D Gaussian Splatting See More Views Than It Is Given
arXiv:2610.07958v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting (3DGS) reconstructs a scene in a single forward pass, replacing per-scene optimization with a network trained across...
arXiv Computation and Language
Sep 30
Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering
arXiv:2609.38177v1 Announce Type: cross Abstract: Reasoning about the 3D world from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While modern MLLMs...
arXiv Computer Vision
Sep 22
GrapeSplat: Geometry-Grounded Reconstruction via Amalgamated Pose-Free Encoding for Feed-Forward 3D Gaussian Splatting
arXiv:2609.23182v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting now reconstructs renderable scenes from unposed, uncalibrated images. Yet, most models supervise only photometric co...