hypernerf.github.io - HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields

home > domains > hypernerf.github.io

Description: HyperNeRF handles topological variations by modeling a family of shapes in a higher-dimensional space, thereby producing more realistic renderings and more accurate geometric reconstructions.

nerf (138) d-nerf (48) nerfies (47) hypernerf (1)

Example domain paragraphs

Here we show results generated with HyperNeRF . These videos show the input video being played back with a stabilized novel camera path. The right side video shows the depth of the scene. Click on the arrows or drag to see more results.

Neural Radiance Fields (NeRF) are able to reconstruct scenes with unprecedented fidelity, and various recent works have extended NeRF to handle dynamic scenes. A common approach to reconstruct such non-rigid scenes is through the use of a learned deformation field mapping from coordinates in each input image into a canonical template coordinate space. However, these deformation-based approaches struggle to model changes in topology, as topological changes require a discontinuity in the deformation field, bu

We address this limitation by lifting NeRFs into a higher dimensional space, and by representing the 5D radiance field corresponding to each individual input image as a slice through this "hyper-space". Our method is inspired by level set methods, which model the evolution of surfaces as slices through a higher dimensional surface. We evaluate our method on two tasks: (i) interpolating smoothly between "moments", i.e., configurations of the scene, seen in the input images while maintaining visual plausibili

Links to hypernerf.github.io (70)

• jonbarron.info Jon Barron
• nerfies.github.io Nerfies: Deformable Neural Radiance Fields
• keunhong.com Keunhong Park
• photoshape.github.io PhotoShape: Photorealistic Materials for Large-Scale Shape Collections — Keunhong Park
• phogzone.com Phogzone | A portfolio for Peter Hedman
• ricardomartinbrualla.com Ricardo Martin-Brualla
• smseitz.com Home
• kerrj.github.io Justin Kerr
• isaac-orbit.github.io ORBIT: A Unified Simulation Framework for Interactive Robot Learning Environments
• autogpart.github.io AutoGPart: Intermediate Supervision Search for Generalizable 3D Part Segmentation
• texturedreamer.github.io TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion
• robotics-fm-survey.github.io Towards General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis
• diffusion-es.github.io Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following
• mcnerf.github.io MCNeRF: Monte Carlo Rendering and Denoising for Real-Time NeRFs
• confaide.github.io Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
• sat2density.github.io Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs
• scenefun3d.github.io SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes
• stitch-time.github.io Stitch it in Time: GAN-Based Facial Editing of Real Videos
• md-splatting.github.io MD-Splatting: Learning Metric Deformation from 4D Gaussians in Highly Deformable Scenes
• camp-nerf.github.io CamP: Camera Preconditioning for Neural Radiance Fields
• dynosaur-it.github.io Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation
• feature-3dgs.github.io Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
• ovmm.github.io HomeRobot: Open Vocabulary Mobile Manipulation
• odin-seg.github.io ODIN: A Single Model For 2D and 3D Perception
• mesh-aware-rf.github.io Dynamic Mesh-Aware Radiance Fields
• scg-rule-guided-music.github.io Symbolic Music Generation with Non-Differentiable Rule Guided Diffusion
• objnerf.github.io Obj-NeRF: Extracting Object NeRFs from Multi-view Images
• lightgaussian.github.io LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS
• equi-articulated-pose.github.io Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance
• rgbmanip.github.io RGBManip: Monocular Image-based Robotic Manipulation through Active Object Pose Estimation
• snnet.github.io Stitchable Neural Networks
• unlearn-canvas.netlify.app UnlearnCanvas: A Stylized Image Dataset to Benchmark Machine Unlearning for Diffusion Models
• chat-with-nerf.github.io Chat with NeRF
• segment3d.github.io Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels
• diffmimic.github.io DiffMimic: Efficient Motion Mimicking with Differentiable Physics
• brics-project.github.io BRICS: Bi-level Feature Representation of Image CollectionS
• adv-icl.github.io Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations
• icgraspnet.github.io ICG-Net: A Unified Approach for Instance-Centric Grasping
• minoring.github.io Minho Heo
• stylegan-nada.github.io StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
• structdiffusion.github.io StructDiffusion: Language-Guided Creation of Physically-Valid Structures using Unseen Objects
• rahimentezari.github.io Rahim Entezari
• flex-nerf.github.io FlexNeRF: Photorealistic Free-viewpoint Rendering of Moving Humans from Sparse Views
• twist-sim2real.github.io TWIST: Teacher-Student World Model Distillation for Efficient Sim-to-Real Transfer
• instantsplat.github.io Instantsplat: Unbounded Sparse-view Pose-free Gaussian Splatting in 40 Seconds
• intrinsic-lora.github.io Generative Models: What do they know?
• image-hijacks.github.io Image Hijacks: Adversarial Images can Control Generative Models at Runtime
• thinshelllab.github.io Thin-shell Object Manipulations with Differentiable Physics Simulations
• codet-ovd.github.io CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection
• scsfnet.github.io Semantic Complete Scene Forecasting from a 4D Dynamic Point Cloud Sequence
• zerotprune.github.io Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers
• masked-spacetime-hashing.github.io Masked Space-Time Hash Encoding
• opennerf.github.io OpenNerf: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views
• controlvideo.github.io ControlVideo: Adding Conditional Control for One Shot Text-to-Video Editing
• hiss-csp.github.io Hierarchical State Space Models for Continuous Sequence-to-Sequence Modeling
• atedm.github.io AT-EDM: Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models
• gpteval3d.github.io GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation
• groma-mllm.github.io Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models
• irisldr.github.io IRIS: Inverse Rendering of Indoor Scenes from Low Dynamic Range Images
• genh2r.github.io GenH2R: Learning Generalizable Human-to-Robot Handover via Scalable Simulation, Demonstration, and Imitation
• isotropic3d.github.io Isotropic3D: Image-to-3D Generation Based on a Single CLIP Embedding
• nerf-course.github.io Home - nerf-course.github.io
• factormatte.github.io FactorMatte: Redefining Video Matting for Re-Composition Tasks
• glushkovato.github.io Taisiya [Taya] Glushkova
• diffusiongpt.github.io DiffusionGPT: LLM-Driven Text-to-Image Generation System
• cpmcorl2023.github.io Composable Part-Based Manipulation
• explorllm.github.io ExploRLLM: Guiding Exploration in Reinforcement Learning with Large Language Models
• parl2024.github.io Learning Planning Abstractions From Language
• rank2reward.github.io Rank2Reward: Learning Shaped Reward Functions from Passive Video
• glee-vision.github.io GLEE:General Object Foundation Model for Images and Videos at Scale