Search Results for author:
Found 42 papers, 8 papers with code
RayZer: A Self-supervised Large View Synthesis Model
The emerging 3D awareness of RayZer is attributed to two key factors.
Gaussian Mixture Flow Matching Models
Diffusion models approximate the denoising distribution as a Gaussian and predict its mean, whereas flow matching models reparameterize the Gaussian mean as flow velocity.
MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data
We propose scaling up 3D scene reconstruction by training with synthesized data.
EP-CFG: Energy-Preserving Classifier-Free Guidance
Classifier-free guidance (CFG) is widely used in diffusion models but often introduces over-contrast and over-saturation artifacts at higher guidance strengths.
Turbo3D: Ultra-fast Text-to-3D Generation
By shifting the Gaussian reconstructor's inputs from pixel space to latent space, we eliminate the extra image decoding time and halve the transformer sequence length for maximum efficiency.
Buffer Anytime: Zero-Shot Video Depth and Normal from Image Priors
We present Buffer Anytime, a framework for estimation of depth and normal maps (which we call geometric buffers) from video that eliminates the need for paired video--depth and video--normal training data.
Generating 3D-Consistent Videos from Unposed Internet Photos
We design a self-supervised method that takes advantage of the consistency of videos and variability of multiview internet photos to train a scalable, 3D-aware video model without any 3D annotations such as camera parameters.
Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats
Unlike previous feed-forward models that are limited to processing 1~4 input images and can only reconstruct a small portion of a large scene, Long-LRM reconstructs the entire scene in a single feed-forward step.
RelitLRM: Generative Relightable Radiance for Large Reconstruction Models
We propose RelitLRM, a Large Reconstruction Model (LRM) for generating high-quality Gaussian splatting representations of 3D objects under novel illuminations from sparse (4-8) posed images captured under unknown static lighting.
PBIR-NIE: Glossy Object Capture under Non-Distant Lighting
Glossy objects present a significant challenge for 3D reconstruction from multi-view input images under natural lighting.
LRM-Zero: Training Large Reconstruction Models with Synthesized Data
We demonstrate that our LRM-Zero, trained with our fully synthesized Zeroverse, can achieve high visual quality in the reconstruction of real-world objects, competitive with models trained on Objaverse.
Neural Gaffer: Relighting Any Object via Diffusion
Single-image relighting is a challenging task that involves reasoning about the complex interplay between geometry, materials, and lighting.
Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling
In contrast to previous methods that use encoding functions with only angular input, we additionally cone-trace spatial features to obtain a spatially varying directional encoding, which addresses the challenging interreflection effects.
GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting
We propose GS-LRM, a scalable large reconstruction model that can predict high-quality 3D Gaussian primitives from 2-4 posed sparse images in 0. 23 seconds on single A100 GPU.
MeshLRM: Large Reconstruction Model for High-Quality Meshes
This allows for end-to-end mesh reconstruction by fine-tuning a pre-trained NeRF LRM with mesh rendering.
DATENeRF: Depth-Aware Text-based Editing of NeRFs
However, extending these techniques to edit scenes in Neural Radiance Fields (NeRF) is complex, as editing individual 2D frames can result in inconsistencies across multiple views.
Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single Image
At the core of portrait photography is the search for ideal lighting and viewpoint.
Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning
To this end, we introduce Carve3D, an improved RLFT algorithm coupled with a novel Multi-view Reconstruction Consistency (MRC) metric, to enhance the consistency of multi-view diffusion models.
PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction
We propose a Pose-Free Large Reconstruction Model (PF-LRM) for reconstructing a 3D object from a few unposed images even with little visual overlap, while simultaneously estimating the relative camera poses in ~1. 3 seconds on a single A100 GPU.
DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model
We propose \textbf{DMV3D}, a novel 3D generation approach that uses a transformer-based 3D large reconstruction model to denoise multi-view diffusion.
LRM: Large Reconstruction Model for Single Image to 3D
We propose the first Large Reconstruction Model (LRM) that predicts the 3D model of an object from a single input image within just 5 seconds.
Controllable Dynamic Appearance for Neural 3D Portraits
The surface normals prediction is guided using 3DMM normals that act as a coarse prior for the normals of the human head, where direct prediction of normals is hard due to rigid and non-rigid deformations induced by head-pose and facial expression changes.
Neural Free-Viewpoint Relighting for Glossy Indirect Illumination
In this paper, we demonstrate a hybrid neural-wavelet PRT solution to high-frequency indirect illumination, including glossy reflection, for relighting with changing view.
NeuManifold: Neural Watertight Manifold Reconstruction with Efficient and High-Quality Rendering Support
We present a method for generating high-quality watertight manifold meshes from multi-view input images.
TensoIR: Tensorial Inverse Rendering
We propose TensoIR, a novel inverse rendering approach based on tensor factorization and neural fields.
PaletteNeRF: Palette-based Appearance Editing of Neural Radiance Fields
Recent advances in neural radiance fields have enabled the high-fidelity 3D reconstruction of complex scenes for novel view synthesis.
ARF: Artistic Radiance Fields
We present a method for transferring the artistic features of an arbitrary style image to a 3D scene.
Differentiable Rendering of Neural SDFs through Reparameterization
Our method leverages the distance to surface encoded in an SDF and uses quadrature on sphere tracer points to compute this warping function.
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.
NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction
We demonstrate that NeRFusion achieves state-of-the-art quality on both large-scale indoor and small-scale object scenes, with substantially faster reconstruction than NeRF and other recent methods.
Point-NeRF: Point-based Neural Radiance Fields
Point-NeRF combines the advantages of these two approaches by using neural 3D point clouds, with associated neural features, to model a radiance field.
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.
NeLF: Neural Light-transport Field for Portrait View Synthesis and Relighting
Our system is trained on a large number of synthetic models, and can generalize to different synthetic and real portraits under various lighting conditions.
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.
Neural Reflectance Fields for Appearance Acquisition
We combine this representation with a physically-based differentiable ray marching framework that can render images from a neural reflectance field under any viewpoint and light.
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.
Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Images
We also show that our learned reflectance volumes are editable, allowing for modifying the materials of the captured scenes.
Deep CG2Real: Synthetic-to-Real Translation via Image Disentanglement
We present a method to improve the visual realism of low-quality, synthetic images, e. g. OpenGL renderings.
Deep 3D Capture: Geometry and Reflectance from Sparse Multi-View Images
We introduce a novel learning-based method to reconstruct the high-quality geometry and complex, spatially-varying BRDF of an arbitrary object from a sparse set of only six images captured by wide-baseline cameras under collocated point lighting.
Deep Hybrid Real and Synthetic Training for Intrinsic Decomposition
Experimental results show that our approach produces better results than the state-of-the-art DL and non-DL methods on various synthetic and real datasets both visually and numerically.
