arXiv Computer Vision
PointForward V2: Point-Aligned Interaction for Feedforward Driving Reconstruction
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 21
HiQGS: Hierarchical Spatiotemporal Querying for Feed-Forward Gaussian Reconstruction
HiQGS is a query-based hierarchical framework that performs feed-forward Gaussian reconstruction from sparse monocular frames. It introduces a Hierarchical Spatiotemporal Encoder that organizes multi-resolution visual features by image location, observation time, and camera pose, preserving complementary appearance and structural cues. A Time-Adaptive Decoder then uses target timestamp queries to retrieve relevant spatiotemporal evidence and predict the corresponding Gaussian scene state, achieving strong rendering quality and geometric accuracy on static and dynamic scene benchmarks.
arXiv Computer Vision
Sep 1
SeqAlign3DVG: A Sequence-Aligned Benchmark and Voxel Reasoning Framework for 3D Visual Grounding
arXiv:2608.30451v1 Announce Type: new Abstract: Image-based 3D visual grounding is critical for embodied agents, yet existing benchmarks suffer from loose text-observation alignment and neglect tempo...
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
Aug 24
Driving with DINO: Vision Foundation Features as a Unified Bridge for Sim-to-Real Generation in Autonomous Driving
The paper introduces Driving with DINO (DwD), a framework that uses Vision Foundation Module (VFM) features to bridge simulation and real-world domains for autonomous driving video generation. It addresses the consistency‑realism dilemma by projecting VFM features onto a principal subspace, dropping high‑frequency texture elements, and applying a Random Channel Tail Drop to preserve structural detail. Additional components— a learnable Spatial Alignment Module and a Causal Temporal Aggregator— enhance control precision, spatial alignment, and temporal stability, reducing motion blur and ensuring realistic, consistent outputs.
arXiv AI
Jul 9
SpaR3D-MoE: Adaptive 3D Spatial Reasoning from Sparse Views Meets Geometry-Inductive Mixture-of-Experts
arXiv:2607. 06620v1 Announce Type: cross Abstract: Recent Multimodal Large Language Models (MLLMs) struggle to bridge the representational gap between 2D semantic understanding and 3D spatial geometry.
arXiv Computer Vision
Sep 23
Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene Reconstruction
arXiv:2609.23796v2 Announce Type: replace Abstract: Single-image 3D object generation can now produce high-fidelity assets, yet accurately placing them into a coherent scene layout remains an open ch...