Related papers: Regulating Intermediate 3D Features for Vision-Cen…
High-quality 3D streaming from multiple cameras is crucial for immersive experiences in many AR/VR applications. The limited number of views - often due to real-time constraints - leads to missing information and incomplete surfaces in the…
We propose a method to learn a high-quality implicit 3D head avatar from a monocular RGB video captured in the wild. The learnt avatar is driven by a parametric face model to achieve user-controlled facial expressions and head poses. Our…
Mobile robots operating indoors must be prepared to navigate challenging scenes that contain transparent surfaces. This paper proposes a novel method for the fusion of acoustic and visual sensing modalities through implicit neural…
Neural volume rendering became increasingly popular recently due to its success in synthesizing novel views of a scene from a sparse set of input images. So far, the geometry learned by neural volume rendering techniques was modeled using a…
Reconstructing a 3D scene from images is challenging due to the different ways light interacts with surfaces depending on the viewer's position and the surface's material. In classical computer graphics, materials can be classified as…
Industrial 3D face assets creation typically reconstructs topology-consistent face meshes from multi-view images for downstream production. However, high-quality reconstruction usually requires manual processing or specific capture…
We present DC-Gaussian, a new method for generating novel views from in-vehicle dash cam videos. While neural rendering techniques have made significant strides in driving scenarios, existing methods are primarily designed for videos…
Imitation learning is a prominent paradigm for robotic manipulation. However, existing visual imitation methods map 2D image observations directly to 3D action outputs, imposing a 2D-3D mismatch that hinders spatial reasoning and degrades…
Recent advances in large vision-language models (VLMs) have shown significant promise for 3D scene understanding. Existing VLM-based approaches typically align 3D scene features with the VLM's embedding space. However, this implicit…
3-D object detection based on 4-D radar-vision is an important part in Internet of Vehicles (IoV). However, there are two challenges which need to be faced. First, the 4-D radar point clouds are sparse, leading to poor 3-D representation.…
Learning robust and scalable visual representations from massive multi-view video data remains a challenge in computer vision and autonomous driving. Existing pre-training methods either rely on expensive supervised learning with 3D…
We present a method that achieves state-of-the-art results for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views. Our algorithm represents a scene…
Single-image 3D scene reconstruction presents significant challenges due to its inherently ill-posed nature and limited input constraints. Recent advances have explored two promising directions: multiview generative models that train on 3D…
We present a novel neural surface reconstruction method, called NeuS, for reconstructing objects and scenes with high fidelity from 2D image inputs. Existing neural surface reconstruction approaches, such as DVR and IDR, require foreground…
Indoor scenes exhibit significant appearance variations due to myriad interactions between arbitrarily diverse object shapes, spatially-changing materials, and complex lighting. Shadows, highlights, and inter-reflections caused by visible…
With virtual reality, digital painting on 2D canvases is now being extended to 3D spaces. Tilt Brush and Oculus Quill are widely accepted among artists as tools that pave the way to a new form of art - 3D emmersive painting. Current 3D…
In crowded urban environments where traffic is dense, current technologies struggle to oversee tight navigation, but surface-level understanding allows autonomous vehicles to safely assess proximity to surrounding obstacles. 3D or 2D scene…
Most automated driving systems comprise a diverse sensor set, including several cameras, Radars, and LiDARs, ensuring a complete 360\deg coverage in near and far regions. Unlike Radar and LiDAR, which measure directly in 3D, cameras capture…
We propose a learning-based approach for novel view synthesis for multi-camera 360$^{\circ}$ panorama capture rigs. Previous work constructs RGBD panoramas from such data, allowing for view synthesis with small amounts of translation, but…
Incrementally recovering 3D dense structures from monocular videos is of paramount importance since it enables various robotics and AR applications. Feature volumes have recently been shown to enable efficient and accurate incremental dense…