Search Results for author:
Found 27 papers, 13 papers with code
Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models
At the core of our approach is Difix, a single-step image diffusion model trained to enhance and remove artifacts in rendered novel views caused by underconstrained regions of the 3D representation.
DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models
Classic physically-based rendering (PBR) accurately simulates the light transport, but relies on precise scene representations--explicit 3D geometry, high-quality material properties, and lighting conditions--that are often impractical to obtain in real-world scenarios.
3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting
3D Gaussian Splatting (3DGS) enables efficient reconstruction and high-fidelity real-time rendering of complex scenes on consumer hardware.
Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos
Recent advancements in static feed-forward scene reconstruction have demonstrated significant progress in high-quality novel view synthesis.
OmniRe: Omni Urban Scene Reconstruction
To that end, we propose a comprehensive 3DGS framework for driving scenes, named OmniRe, that allows for accurate, full-length reconstruction of diverse dynamic objects in a driving log.
Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering
The correct insertion of virtual objects in images of real-world scenes requires a deep understanding of the scene's lighting, geometry and materials, as well as the image formation process.
3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes
The benefits of ray tracing are well-known in computer graphics: processing incoherent rays for secondary lighting effects such as shadows and reflections, rendering from highly-distorted cameras common in robotics, stochastically sampling rays, and more.
Outdoor Scene Extrapolation with Hierarchical Generative Cellular Automata
We aim to generate fine-grained 3D geometry from large-scale sparse LiDAR scans, abundantly captured by autonomous vehicles (AV).
Memorize What Matters: Emergent Scene Decomposition from Multitraverse
Humans naturally retain memories of permanent elements, while ephemeral moments often slip through the cracks of memory.
RefFusion: Reference Adapted Diffusion Models for 3D Scene Inpainting
In this work, we propose an approach for 3D scene inpainting -- the task of coherently replacing parts of the reconstructed scene with desired content.
Adaptive Shells for Efficient Neural Radiance Field Rendering
We then extract an explicit mesh of a narrow band around the surface, with width determined by the kernel size, and fine-tune the radiance field within this band.
Towards Viewpoint Robustness in Bird's Eye View Segmentation
We introduce a technique for novel view synthesis and use it to transform collected data to the viewpoint of target rigs, allowing us to train BEV segmentation models for diverse target rigs without any additional data collection or labeling cost.
Flexible Isosurface Extraction for Gradient-Based Mesh Optimization
This work considers gradient-based mesh optimization, where we iteratively optimize for a 3D surface mesh by representing it as the isosurface of a scalar field, an increasingly common paradigm in applications including photogrammetry, generative modeling, and inverse physics.
Neural Kernel Surface Reconstruction
We present a novel method for reconstructing a 3D implicit surface from a large-scale, sparse, and noisy point cloud.
Neural LiDAR Fields for Novel View Synthesis
We present Neural Fields for LiDAR (NFL), a method to optimise a neural field scene representation from LiDAR measurements, with the goal of synthesizing realistic LiDAR scans from novel viewpoints.
Neural Fields meet Explicit Geometric Representation for Inverse Rendering of Urban Scenes
Reconstruction and intrinsic decomposition of scenes from captured imagery would enable many applications such as relighting and virtual object insertion.
Neural Fields Meet Explicit Geometric Representations for Inverse Rendering of Urban Scenes
Reconstruction and intrinsic decomposition of scenes from captured imagery would enable many applications such as relighting and virtual object insertion.
LION: Latent Point Diffusion Models for 3D Shape Generation
To advance 3D DDMs and make them useful for digital artists, we require (i) high generation quality, (ii) flexibility for manipulation and applications such as conditional synthesis and shape interpolation, and (iii) the ability to output smooth surfaces or meshes.
Ranked #1 on
Point Cloud Generation
on ShapeNet Airplane
GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images
As several industries are moving towards modeling massive 3D virtual worlds, the need for content creation tools that can scale in terms of the quantity, quality, and diversity of 3D content is becoming evident.
Dynamic 3D Scene Analysis by Point Cloud Accumulation
Compared to state-of-the-art scene flow estimators, our proposed approach aims to align all 3D points in a common reference frame correctly accumulating the points on the individual objects.
Neural Fields as Learnable Kernels for 3D Reconstruction
We present Neural Kernel Fields: a novel method for reconstructing implicit 3D shapes based on a learned kernel ridge regression.
Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronization
We present SyNoRiM, a novel way to jointly register multiple non-rigid shapes by synchronizing the maps relating learned functions defined on the point clouds.
Weakly Supervised Learning of Rigid 3D Scene Flow
We propose a data-driven scene flow estimation algorithm exploiting the observation that many 3D scenes can be explained by a collection of agents moving as rigid bodies.
PREDATOR: Registration of 3D Point Clouds with Low Overlap
We introduce PREDATOR, a model for pairwise point-cloud registration with deep attention to the overlap region.
CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations
We propose CaSPR, a method to learn object-centric Canonical Spatiotemporal Point Cloud Representations of dynamically moving or evolving objects.
Learning multiview 3D point cloud registration
We present a novel, end-to-end learnable, multiview 3D point cloud registration algorithm.
The Perfect Match: 3D Point Cloud Matching with Smoothed Densities
Our approach is sensor- and sceneagnostic because of SDV, LRF and learning highly descriptive features with fully convolutional layers.
Ranked #4 on
Point Cloud Registration
on ETH (trained on 3DMatch)
