Related papers: SRUG: Shadow-Guided Relightable Urban Scene with G…
Accurate reconstruction and relighting of glossy objects remains a longstanding challenge, as object shape, material properties, and illumination are inherently difficult to disentangle. Existing neural rendering approaches often rely on…
Reconstructing urban scenes is challenging due to their complex geometries and the presence of potentially dynamic objects. 3D Gaussian Splatting (3DGS)-based methods have shown strong performance, but existing approaches often incorporate…
We present InvRGB+L, a novel inverse rendering model that reconstructs large, relightable, and dynamic scenes from a single RGB+LiDAR sequence. Conventional inverse graphics methods rely primarily on RGB observations and use LiDAR mainly…
Low Dynamic Range (LDR) to High Dynamic Range (HDR) image translation is a fundamental task in many computational vision problems. Numerous data-driven methods have been proposed to address this problem; however, they lack explicit modeling…
Low-light image enhancement aims to improve an image's visibility while keeping its visual naturalness. Different from existing methods tending to accomplish the relighting task directly by ignoring the fidelity and naturalness recovery, we…
By supervising camera rays between a scene and multi-view image planes, NeRF reconstructs a neural scene representation for the task of novel view synthesis. On the other hand, shadow rays between the light source and the scene have yet to…
We introduce SynthLight, a diffusion model for portrait relighting. Our approach frames image relighting as a re-rendering problem, where pixels are transformed in response to changes in environmental lighting conditions. Using a…
Humans can naturally identify and mentally complete occluded objects in cluttered environments. However, imparting similar cognitive ability to robotics remains challenging even with advanced reconstruction techniques, which models scenes…
Recent deep learning methods have achieved promising results in image shadow removal. However, their restored images still suffer from unsatisfactory boundary artifacts, due to the lack of degradation prior embedding and the deficiency in…
Recent advancements in text-to-3D generation, building on the success of high-performance text-to-image generative models, have made it possible to create imaginative and richly textured 3D objects from textual descriptions. However, a key…
We address the problem of generating a 3D-consistent, navigable environment that is spatially grounded: a simulation of a real location. Existing video generative models can produce a plausible sequence that is consistent with a text (T2V)…
Single image scene relighting aims to generate a realistic new version of an input image so that it appears to be illuminated by a new target light condition. Although existing works have explored this problem from various perspectives,…
Recent advances in illumination control extend image-based methods to video, yet still facing a trade-off between lighting fidelity and temporal consistency. Moving beyond relighting, a key step toward generative modeling of real-world…
The task of separating dynamic objects from static environments using NeRFs has been widely studied in recent years. However, capturing large-scale scenes still poses a challenge due to their complex geometric structures and unconstrained…
We propose GRGS, a generalizable and relightable 3D Gaussian framework for high-fidelity human novel view synthesis under diverse lighting conditions. Unlike existing methods that rely on per-character optimization or ignore physical…
Decomposing an object's appearance into representations of its materials and the surrounding illumination is difficult, even when the object's 3D shape is known beforehand. This problem is especially challenging for diffuse objects: it is…
Urban scene reconstruction from real-world observations has emerged as a powerful tool for self-driving development and testing. While current neural rendering approaches achieve high-fidelity rendering along the recorded trajectories,…
We present a new pipeline for holistic 3D scene understanding from a single image, which could predict object shapes, object poses, and scene layout. As it is a highly ill-posed problem, existing methods usually suffer from inaccurate…
Recent approaches for 3D relighting have shown promise in integrating 2D image relighting generative priors to alter the appearance of a 3D representation while preserving the underlying structure. Nevertheless, generative priors used for…
Scene graph generation (SGG) aims to understand the visual objects and their semantic relationships from one given image. Until now, lots of SGG datasets with the eyelevel view are released but the SGG dataset with the overhead view is…