Related papers: Geo-EVS: Geometry-Conditioned Extrapolative View S…
Localization in GNSS-denied and GNSS-degraded environments is a challenge for the safe widespread deployment of autonomous vehicles. Such GNSS-challenged environments require alternative methods for robust localization. In this work, we…
The task of generating natural images from 3D scenes has been a long standing goal in computer graphics. On the other hand, recent developments in deep neural networks allow for trainable models that can produce natural-looking images with…
Autoregressive models are structurally misaligned with the inherently parallel nature of geospatial understanding, forcing a rigid sequential narrative onto scenes and fundamentally hindering the generation of structured and coherent…
The enduring inability of image generative models to recreate intricate geometric features, such as those present in human hands and fingers has been an ongoing problem in image generation for nearly a decade. While strides have been made…
Drone-view geo-localization aims to match a query drone image, often captured under adverse weather conditions (e.g., rain, snow, fog), against a gallery of geo-tagged satellite images. Weather-induced degradations in the drone view, such…
Autoregressive video diffusion models are capable of long rollouts that are stable and consistent with history, but they are unable to guide the current generation with conditioning from the future. In camera-guided video generation with a…
Large-scale scene data is essential for training and testing in robot learning. Neural reconstruction methods have promised the capability of reconstructing large physically-grounded outdoor scenes from captured sensor data. However, these…
Novel View Synthesis (NVS) for street scenes play a critical role in the autonomous driving simulation. The current mainstream technique to achieve it is neural rendering, such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting…
Gaussian Splatting has achieved remarkable progress in multi-view surface reconstruction, yet it exhibits notable degradation when only few views are available. Although recent efforts alleviate this issue by enhancing multi-view…
Driving view synthesis along free-form trajectories is essential for realistic driving simulations, enabling closed-loop evaluation of end-to-end driving policies. Existing methods excel at view interpolation along recorded paths but…
Novel View Synthesis (NVS) from sparse views presents a formidable challenge in 3D reconstruction, where limited multi-view constraints lead to severe overfitting, geometric distortion, and fragmented scenes. While 3D Gaussian Splatting…
We present a novel approach, termed ADGaussian, for generalizable street scene reconstruction. The proposed method enables high-quality rendering from merely single-view input. Unlike prior Gaussian Splatting methods that primarily focus on…
Novel view synthesis (NVS) through non-planar refractive surfaces presents fundamental challenges due to severe, spatially varying optical distortions. While recent representations like NeRF and 3D Gaussian Splatting (3DGS) excel at NVS,…
Recent GS-based rendering has made significant progress for LiDAR, surpassing Neural Radiance Fields (NeRF) in both quality and speed. However, these methods exhibit artifacts in extrapolated novel view synthesis due to the incomplete…
Reconstructing accurate surfaces with radiance fields has achieved remarkable progress in recent years. However, prevailing approaches, primarily based on Gaussian Splatting, are increasingly constrained by representational bottlenecks. In…
Event cameras offer promising advantages such as high dynamic range and low latency, making them well-suited for challenging lighting conditions and fast-moving scenarios. However, reconstructing 3D scenes from raw event streams is…
We introduce a 3D-aware diffusion model, ZeroNVS, for single-image novel view synthesis for in-the-wild scenes. While existing methods are designed for single objects with masked backgrounds, we propose new techniques to address challenges…
Vehicle Re-identification (Re-ID) has been broadly studied in the last decade; however, the different camera view angle leading to confused discrimination in the feature subspace for the vehicles of various poses, is still challenging for…
Recent 3D reconstruction methods achieve impressive results with dense multi-view imagery but struggle when only a few views are available. Various approaches, including regularization techniques, semantic priors, and geometric constraints,…
Recent advances in 3D Gaussian Splatting (3DGS) enable real-time, high-fidelity novel view synthesis (NVS) with explicit 3D representations. However, performance degradation and instability remain significant under sparse-view conditions.…