arXiv AI
Jun 4
DVGT: Driving Visual Geometry Transformer
arXiv:2512. 16919v2 Announce Type: replace-cross Abstract: Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving.
Geometry-Grounded Unified 3D Perception for Autonomous Driving
Related stories
arXiv Computer Vision
Sep 16
NeuroSymbEAD: A Large Scale Neuro-Symbolic Caption Dataset for Omni-Directional Embodied Autonomous Driving
NeuroSymbEAD is a large‑scale neuro‑symbolic caption dataset that builds an ego‑centric knowledge graph of static and dynamic objects on the KITTI‑360 dataset, annotating classes, categories, heading directions, orientations, and distances from the ego‑vehicle. The dataset generates multilevel textual captions that serve as a lightweight representation of an ego‑centric scene map, enabling outdoor scene‑map reconstruction, visual recognition, and object grounding. Baselines for driving common sense and traffic/scene understanding are established, and the dataset is benchmarked using pre‑trained grounding and learned auto‑regressive captioning networks to support vision‑language and foundation models for traffic‑scene explanation, 3D reasoning, and interpretable autonomous‑driving perception.
arXiv Computer Vision
Sep 7
Object Concepts Emerge from Motion
The paper introduces a biologically inspired framework that learns object‑centric visual representations from raw videos without human annotations or camera calibration. By using motion boundaries detected via optical flow and clustering to create pseudo‑instance masks, the method supervises a single‑image encoder with pixel‑level pairwise metric learning. Training on 195 million pseudo‑labeled frames and expanding to 421 million frames through Motion‑Verified Self‑Training, the approach yields Swin‑based encoders that outperform or match supervised and self‑supervised baselines on tasks such as monocular depth estimation, 3D object detection, 3D occupancy prediction, and end‑to‑end planning.
arXiv Computer Vision
Aug 24
GS-Net: Heterogeneous Vehicle Data Reuse via Generalizable Plug-and-Play 3DGS Module
GS‑Net is a lightweight plug‑and‑play module that expands sparse Structure‑from‑Motion point clouds into dense Gaussian primitives, enabling cross‑sensor view synthesis for autonomous driving. It learns a generalizable initialization for 3D Gaussian Splatting, improving rendering quality for both interpolated and extrapolated camera viewpoints. The authors introduce CARLA‑NVS, a benchmark with 12 uniformly spaced cameras, and show that GS‑Net outperforms standard 3DGS by 2.08 dB PSNR on interpolated views and 1.86 dB on extrapolated views while being 50× faster to initialize.
arXiv Computer Vision
Sep 7
CrossDepth: Geometry-Constrained Attention for Generalizable Multi-View Surround Depth Estimation
CrossDepth introduces geometry-constrained attention for multi-view surround depth estimation, addressing cross-image inconsistencies caused by varying camera intrinsics and limited receptive fields. The method conditions features on per-pixel camera-aware ray embeddings and extends pixel context via cross-image attention limited to geometrically plausible regions. Trained self-supervised with photometric consistency, it achieves better depth accuracy and consistency on DDAD and nuScenes compared to existing self-supervised approaches.
arXiv Computer Vision
Sep 3
TAPVid-MV: A Benchmark for Tracking Any Point in 3D Across Multiple Views
TAPVid-MV is a new benchmark for tracking any point in 3D across multiple synchronized camera views. It comprises 284 sequences, 1,142 calibrated camera streams, and 109,769 point tracks, covering indoor and outdoor domains and derived from various modalities such as depth, LiDAR, SLAM, and simulation. The dataset is visually verified, and evaluation shows that current multi‑view trackers do not consistently outperform monocular trackers, highlighting geometry recovery as a key bottleneck.
arXiv Computer Vision
Oct 5
FRUC: Feedforward Dynamic Scene Reconstruction from Uncalibrated Collaborative Driving Views
FRUC is a feedforward 3D Gaussian Splatting framework that reconstructs dynamic scenes from uncalibrated collaborative driving views. It uses a visual‑grounded geometric Transformer backbone for one‑shot, calibration‑free inference and introduces an ego‑centric causal occlusion field to model occlusion evolution across agents. The method performs cross‑agent integration as a deterministic residual denoising process, achieving state‑of‑the‑art rendering quality and efficiency on V2X‑Real and UrbanIng‑V2X datasets.
arXiv AI
Jul 7
MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources
arXiv:2601. 22054v2 Announce Type: replace-cross Abstract: Scaling has powered recent advances in vision foundation models, yet extending this paradigm to metric depth estimation remains challenging due to heterogeneous sensor noise, camera-dependent biases, and metric ambiguity in noisy cross-source 3D data.
arXiv Computer Vision
Oct 9
HENet++: Hybrid Encoding and Multi-task Learning for 3D Perception and End-to-end Autonomous Driving
HENet++ is a unified framework that combines a hybrid image encoding strategy—using a large encoder for short‑term frames and a lightweight encoder for long‑term temporal context—to balance accuracy and efficiency in 3D perception for autonomous driving. It jointly extracts dense background and sparse foreground features, enabling task‑specific representations that reduce cumulative errors and enrich downstream prediction and planning modules. The approach supports diverse 3D feature extraction pipelines, multi‑modal inputs (camera and radar), and achieves state‑of‑the‑art results on nuScenes and NAVSIM benchmarks, including the lowest collision rate on nuScenes planning.
arXiv AI
Jul 24
3D-Aware VLMs with Implicit and Explicit Geometries
arXiv:2607. 21595v1 Announce Type: cross Abstract: Despite rapid progress, most existing vision-language models (VLMs) built from 2D visual inputs often struggle when handling various 3D tasks that require fine-grained spatial understanding and reasoning.
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.
Hugging Face Trending Papers
Sep 8
DXPR: Depth-Based Vision-LiDAR Cross-Modal Place Recognition Using Vision Foundation Models
DXPR is a depth‑based cross‑modal place recognition framework that matches monocular camera queries to a LiDAR map using a single vision foundation model backbone. By converting both modalities into a unified depth image representation, DXPR learns modality‑invariant global descriptors without modality‑specific encoders. A geometry‑aware overlap miner refines pairwise metric learning by computing pixel‑level overlap scores, and extensive tests on KITTI and Boreas show strong performance across seasons, weather, and day/night conditions, outperforming prior CMPR baselines.