Related papers: HOMER: Homography-Based Efficient Multi-view 3D Ob…
3D printing has revolutionized the manufacturing of volumetric components and structures in many areas. Different technologies have been developed including light-induced techniques based on the photopolymerization of liquid resins. In…
3D spatial perception is fundamental to generalizable robotic manipulation, yet obtaining reliable, high-quality 3D geometry remains challenging. Depth sensors suffer from noise and material sensitivity, while existing reconstruction models…
We present ONeRF, a method that automatically segments and reconstructs object instances in 3D from multi-view RGB images without any additional manual annotations. The segmented 3D objects are represented using separate Neural Radiance…
Recent advances in Novel View Synthesis (NVS) and 3D generation have significantly improved editing tasks, with a primary emphasis on maintaining cross-view consistency throughout the generative process. Contemporary methods typically…
We propose a scene-level inverse rendering framework that uses multi-view images to decompose the scene into geometry, a SVBRDF, and 3D spatially-varying lighting. Because multi-view images provide a variety of information about the scene,…
We propose a system that learns to detect objects and infer their 3D poses in RGB-D images. Many existing systems can identify objects and infer 3D poses, but they heavily rely on human labels and 3D annotations. The challenge here is to…
Image space feature detection is the act of selecting points or parts of an image that are easy to distinguish from the surrounding image region. By combining a repeatable point detection with a descriptor, parts of an image can be matched…
Conventional video segmentation approaches rely heavily on appearance models. Such methods often use appearance descriptors that have limited discriminative power under complex scenarios. To improve the segmentation performance, this paper…
Image-based object removal often erases only the named target, leaving behind interaction evidence that renders the result semantically inconsistent. We formalize this problem as Interaction-Consistent Object Removal (ICOR), which requires…
Image anomaly detection plays a vital role in applications such as industrial quality inspection and medical imaging, where it directly contributes to improving product quality and system reliability. However, existing methods often…
Text-to-3D form plays a crucial role in creating editable 3D scenes for AR/VR. Recent advances have shown promise in merging neural radiance fields (NeRFs) with pre-trained diffusion models for text-to-3D object generation. However, one…
We propose an optimization technique for 3-D underwater object modeling from 2-D forward-scan sonar images at known poses. A key contribution, for objects imaged in the proximity of the sea surface, is to resolve the multipath artifacts due…
3D rendering of dynamic face captures is a challenging problem, and it demands improvements on several fronts$\unicode{x2014}$photorealism, efficiency, compatibility, and configurability. We present a novel representation that enables…
Solving image-to-3D from a single view is an ill-posed problem, and current neural reconstruction methods addressing it through diffusion models still rely on scene-specific optimization, constraining their generalization capability. To…
Representing scenes from multi-view images is a crucial task in computer vision with extensive applications. However, inherent photometric distortions in the camera imaging can significantly degrade image quality. Without accounting for…
Simultaneous perception of 2D objects in perspective view and 3D objects in Bird's Eye View (BEV) is challenging for multi-camera autonomous driving. Existing two-stage pipelines use 2D results only as a one-time cue for 3D detection. We…
In autonomous driving, LiDAR sensors are vital for acquiring 3D point clouds, providing reliable geometric information. However, traditional sampling methods of preprocessing often ignore semantic features, leading to detail loss and ground…
Existing state-of-the-art methods for Video Object Segmentation (VOS) learn low-level pixel-to-pixel correspondences between frames to propagate object masks across video. This requires a large amount of densely annotated video data, which…
3D semantic occupancy prediction is a pivotal task in the field of autonomous driving. Recent approaches have made great advances in 3D semantic occupancy predictions on a single modality. However, multi-modal semantic occupancy prediction…
Object manipulation in images aims to not only edit the object's presentation but also gift objects with motion. Previous methods encountered challenges in concurrently handling static editing and dynamic generation, while also struggling…