Search Results for author:
Found 21 papers, 3 papers with code
3D Mesh Editing using Masked LRMs
We formulate shape editing as a conditional reconstruction problem, where the model must reconstruct the input shape with the exception of a specified 3D region, in which the geometry should be generated from the conditional signal.
NeRF Analogies: Example-Based Visual Attribute Transfer for NeRFs
A Neural Radiance Field (NeRF) encodes the specific relation of 3D geometry and appearance of a scene.
ReplaceAnything3D:Text-Guided 3D Scene Editing with Compositional Neural Radiance Fields
We introduce ReplaceAnything3D model (RAM3D), a novel text-guided 3D scene editing method that enables the replacement of specific objects within a scene.
IRIS: Inverse Rendering of Indoor Scenes from Low Dynamic Range Images
While numerous 3D reconstruction and novel-view synthesis methods allow for photorealistic rendering of a scene from multi-view images easily captured with consumer cameras, they bake illumination in their representations and fall short of supporting advanced applications like material editing, relighting, and virtual object insertion.
TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion
In contrast, TextureDreamer can transfer highly detailed, intricate textures from real-world environments to arbitrary objects with only a few casually captured images, potentially significantly democratizing texture creation.
GauFRe: Gaussian Deformation Fields for Real-time Dynamic Novel View Synthesis
Specifically, we propose a template set of 3D Gaussians residing in a canonical space, and a time-dependent forward-warping deformation field to model dynamic objects.
Efficient Graphics Representation with Differentiable Indirection
We introduce differentiable indirection -- a novel learned primitive that employs differentiable multi-scale lookup tables as an effective substitute for traditional compute and data operations across the graphics pipeline.
Spatiotemporally Consistent HDR Indoor Lighting Estimation
For training, we significantly enhance the OpenRooms public dataset of photorealistic synthetic indoor scenes with around 360K HDR environment maps of much higher resolution and 38K video sequences, rendered with GPU-based path tracing.
Neural-PBIR Reconstruction of Shape, Material, and Illumination
In the last stage, initialized by the neural predictions, we perform PBIR to refine the initial results and obtain the final high-quality reconstruction of object shape, material, and illumination.
Ranked #1 on
Depth Prediction
on Stanford-ORB
PhotoScene: Photorealistic Material and Lighting Transfer for Indoor Scenes
Most indoor 3D scene reconstruction methods focus on recovering 3D geometry and scene layout.
IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenes
Indoor scenes exhibit significant appearance variations due to myriad interactions between arbitrarily diverse object shapes, spatially-changing materials, and complex lighting.
Physically-Based Editing of Indoor Scene Lighting from a Single Image
We tackle this problem using two novel components: 1) a holistic scene reconstruction method that estimates scene reflectance and parametric 3D lighting, and 2) a neural rendering framework that re-renders the scene from our predictions.
Learning Neural Transmittance for Efficient Rendering of Reflectance Fields
However, it remains challenging and time-consuming to render such representations under complex lighting such as environment maps, which requires individual ray marching towards each single light to calculate the transmittance at every sampled point.
OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets
Finally, we demonstrate that our framework may also be integrated with physics engines, to create virtual robotics environments with unique ground truth such as friction coefficients and correspondence to real scenes.
OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets
Finally, we demonstrate that our framework may also be integrated with physics engines, to create virtual robotics environments with unique ground truth such as friction coefficients and correspondence to real scenes.
Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes
Recovering the 3D shape of transparent objects using a small number of unconstrained natural images is an ill-posed problem.
Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Image
Our inverse rendering network incorporates physical insights -- including a spatially-varying spherical Gaussian lighting representation, a differentiable rendering layer to model scene appearance, a cascade structure to iteratively refine the predictions and a bilateral solver for refinement -- allowing us to jointly reason about shape, lighting, and reflectance.
Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image
We propose a material acquisition approach to recover the spatially-varying BRDF and normal map of a near-planar surface from a single image captured by a handheld mobile phone camera.
Robust Energy Minimization for BRDF-Invariant Shape From Light Fields
On the other hand, recent works have explored PDE invariants for shape recovery with complex BRDFs, but they have not been incorporated into robust numerical optimization frameworks.
Automatic Image Cropping : A Computational Complexity Study
Attention based automatic image cropping aims at preserving the most visually important region in an image.
Superpixel Segmentation Using Linear Spectral Clustering
We present in this paper a superpixel segmentation algorithm called Linear Spectral Clustering (LSC), which produces compact and uniform superpixels with low computational costs.
