可阅读全文PAPER
3D Gaussian Splatting for Real-Time Radiance Field Rendering
阅读精读
A PERSONAL RESEARCH LIBRARY
从一篇论文，
读懂一个方向。
连接问题、方法与研究者。沿着已有的研究分类探索论文，
让每一次精读，成为下一步思考的起点。
165
索引论文
174
可读精读页
3
预留位置
全部论文
可阅读全文PAPER
3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks
阅读精读
可阅读全文PAPER
3D Sketching using Multi-View Deep Volumetric Prediction
阅读精读
可阅读全文PAPER
5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks
阅读精读
可阅读全文PAPER
A Comparison Between 3D Reconstruction Using NeRF Neural Networks and MVS Algorithms on Cultural Heritage Images
阅读精读
可阅读全文PAPER
A Divide et Impera Approach for 3D Shape Reconstruction from Multiple Views
阅读精读
可阅读全文PAPER
A Semi-Procedural Convolutional Material Prior
阅读精读
可阅读全文PAPER
ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer
阅读精读
可阅读全文PAPER
ACE++: Instruction-Based Image Creation and Editing via Context-Aware Content Filling
阅读精读
可阅读全文PAPER
Adding Conditional Control to Text-to-Image Diffusion Models
阅读精读
可阅读全文PAPER
Adversarial Single-Image SVBRDF Estimation with Hybrid Training
阅读精读
可阅读全文PAPER
Alchemist: Parametric Control of Material Properties with Diffusion Models
阅读精读
可阅读全文PAPER
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
阅读精读
可阅读全文PAPER
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
阅读精读
可阅读全文PAPER
An Introduction to Variational Autoencoders
阅读精读
可阅读全文PAPER
Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
阅读精读
可阅读全文PAPER
ArtCrafter: Text-Image Aligning Style Transfer via Embedding Reframing
阅读精读
可阅读全文PAPER
Attention Is All You Need
阅读精读
可阅读全文PAPER
AutoHarness: improving LLM agents by automatically synthesizing a code harness
阅读精读
可阅读全文PAPER
AVID: Any-Length Video Inpainting with Diffusion Model
阅读精读
可阅读全文PAPER
Blended Latent Diffusion
阅读精读
可阅读全文PAPER
Block-NeRF: Scalable Large Scene Neural View Synthesis
阅读精读
可阅读全文PAPER
CameraCtrl: Enabling Camera Control for Video Diffusion Models
阅读精读
可阅读全文PAPER
CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models
阅读精读
可阅读全文PAPER
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
阅读精读
可阅读全文PAPER
CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets
阅读精读
可阅读全文PAPER
CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields
阅读精读
可阅读全文PAPER
CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility
阅读精读
可阅读全文PAPER
ControlMat: A Controlled Generative Approach to Material Capture
阅读精读
可阅读全文PAPER
Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model
阅读精读
可阅读全文PAPER
D3: Data-Driven Documents
阅读精读
可阅读全文PAPER
De-rendering Stylized Texts
阅读精读
可阅读全文PAPER
Deep Marching Cubes: Learning Explicit Surface Representations
阅读精读
可阅读全文PAPER
Deep Unsupervised Learning using Nonequilibrium Thermodynamics
阅读精读
可阅读全文PAPER
DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation
阅读精读
可阅读全文PAPER
DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning
阅读精读
可阅读全文PAPER
Deferred Neural Rendering: Image Synthesis using Neural Textures
阅读精读
可阅读全文PAPER
DeformNet: Free-Form Deformation Network for 3D Shape Reconstruction from a Single Image
阅读精读
可阅读全文PAPER
DEFT-VTON: Efficient Virtual Try-On with Consistent Generalised H-Transform
阅读精读
可阅读全文PAPER
DEFT: Efficient Fine-Tuning of Diffusion Models by Learning the Generalised h-transform
阅读精读
可阅读全文PAPER
Demystifying Flux Architecture
阅读精读
可阅读全文PAPER
Denoising Diffusion Implicit Models
阅读精读
可阅读全文PAPER
Denoising Diffusion Probabilistic Models
阅读精读
可阅读全文PAPER
DiffMat: Latent diffusion models for image-guided material generation
阅读精读
可阅读全文PAPER
Diffusion Models for Video Prediction and Infilling
阅读精读
可阅读全文PAPER
Diffusion Models in Vision: A Survey
阅读精读
可阅读全文PAPER
Diffusion Texture Painting
阅读精读
可阅读全文PAPER
Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion
阅读精读
可阅读全文PAPER
Dream-RSI: Recursive Self-Improvement through Evolving Worlds
阅读精读
可阅读全文PAPER
DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
阅读精读
可阅读全文PAPER
DreamFusion: Text-to-3D using 2D Diffusion
阅读精读
可阅读全文PAPER
DyDiT++: Dynamic Diffusion Transformers for Efficient Visual Generation
阅读精读
可阅读全文PAPER
earPod: Eyes-free Menu Selection using Touch Input and Reactive Audio Feedback
阅读精读
可阅读全文PAPER
EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer
阅读精读
可阅读全文PAPER
End-to-end Procedural Material Capture with Proxy-Free Mixed-Integer Optimization
阅读精读
可阅读全文PAPER
Flow Matching for Generative Modeling
阅读精读
可阅读全文PAPER
Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
阅读精读
可阅读全文PAPER
FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
阅读精读
可阅读全文PAPER
Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models
阅读精读
可阅读全文PAPER
Generating Procedural Materials from Text or Image Prompts
阅读精读
可阅读全文PAPER
Generative Image Dynamics
阅读精读
可阅读全文PAPER
Generative Modeling by Estimating Gradients of the Data Distribution
阅读精读
可阅读全文PAPER
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
阅读精读
可阅读全文PAPER
GNeRF: GAN-based Neural Radiance Field without Posed Camera
阅读精读
可阅读全文PAPER
Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise
阅读精读
可阅读全文PAPER
Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editing
阅读精读
可阅读全文PAPER
h-Edit: Effective and Flexible Diffusion-Based Editing via Doob's h-Transform
阅读精读
可阅读全文PAPER
HCI Research as Problem-Solving
阅读精读
可阅读全文PAPER
High-Resolution Image Synthesis with Latent Diffusion Models
阅读精读
可阅读全文PAPER
How I Warped Your Noise: A Temporally-Correlated Noise Prior for Diffusion Models
阅读精读
可阅读全文PAPER
Human Motion Transfer with 3D Constraints and Detail Enhancement
阅读精读
可阅读全文PAPER
Image sculpting: Precise object editing with 3d geometry control
阅读精读
可阅读全文PAPER
Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era
阅读精读
可阅读全文PAPER
Improving Diffusion Models for Authentic Virtual Try-on in the Wild
阅读精读
可阅读全文PAPER
Interpretable procedural material graph generation via diffusion models from reference images
阅读精读
可阅读全文PAPER
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
阅读精读
可阅读全文PAPER
Language-based Photo Color Adjustment for Graphic Designs.
阅读精读
可阅读全文PAPER
Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures
阅读精读
可阅读全文PAPER
Learning Transferable Visual Models From Natural Language Supervision
阅读精读
可阅读全文PAPER
Lifting Freehand Concept Sketches into 3D
阅读精读
可阅读全文PAPER
Loosecontrol: Lifting controlnet for generalized depth conditioning
阅读精读
可阅读全文PAPER
LoRA: Low-Rank Adaptation of Large Language Models
阅读精读
精读待补充PAPER
LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation
已预留文章位置
精读待补充PAPER
MAIR: Multi-view Attention Inverse Rendering with 3D Spatially-Varying Lighting Estimation
已预留文章位置
精读待补充PAPER
MAIR++: Improving Multi-view Attention Inverse Rendering with Implicit Lighting Representation
已预留文章位置
可阅读全文PAPER
MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation
阅读精读
可阅读全文PAPER
MaPa: Text-driven Photorealistic Material Painting for 3D Shapes
阅读精读
可阅读全文PAPER
MARBLE: Material Recomposition and Blending in CLIP-Space
阅读精读
可阅读全文PAPER
MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing
阅读精读
可阅读全文PAPER
MATch: Differentiable Material Graphs for Procedural Material Capture
阅读精读
可阅读全文PAPER
MaTe: Images Are All You Need for Material Transfer via Diffusion Transformer
阅读精读
可阅读全文PAPER
Material Editing Using a Physically Based Rendering Network
阅读精读
可阅读全文PAPER
Material Palette: Extraction of Materials from a Single Image
阅读精读
可阅读全文PAPER
MaterialFusion: High-Quality, Zero-Shot, and Controllable Material Transfer with Diffusion Models
阅读精读
可阅读全文PAPER
MaterialPicker: Multi-Modal Material Generation with Diffusion Transformers
阅读精读
可阅读全文PAPER
MatFormer: A Generative Model for Procedural Materials
阅读精读
可阅读全文PAPER
MatFuse: Controllable Material Generation with Diffusion Models
阅读精读
可阅读全文PAPER
MatFusion: A Generative Diffusion Model for SVBRDF Capture
阅读精读
可阅读全文PAPER
MatSwap: Light-aware material transfers in images
阅读精读
可阅读全文PAPER
Mean Flows for One-step Generative Modeling
阅读精读
可阅读全文PAPER
Mix-of-show: Decentralized low-rank adaptation for multi-concept customization of diffusion models
阅读精读
可阅读全文PAPER
MultiMat: Multimodal Program Synthesis for Procedural Materials using Large Multimodal Models
阅读精读
可阅读全文PAPER
NeRF--: Neural Radiance Fields Without Known Camera Parameters
阅读精读
可阅读全文PAPER
NeRF-Texture: Texture Synthesis with Neural Radiance Fields
阅读精读
可阅读全文PAPER
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
阅读精读
可阅读全文PAPER
Not All Spacings are Created Equal: The Effect of Text Spacings in On-the-go Reading Using Optical See-Through Head-Mounted Displays
阅读精读
可阅读全文PAPER
Object 3dit: Language-guided 3d-aware image editing
阅读精读
可阅读全文PAPER
Ominicontrol: Minimal and universal control for diffusion transformer
阅读精读
可阅读全文PAPER
One-step Latent-free Image Generation with Pixel Mean Flows
阅读精读
可阅读全文PAPER
Paint by Example: Exemplar-based Image Editing with Diffusion Models
阅读精读
可阅读全文PAPER
Parallel Prototyping Leads to Better Design Results, More Divergence, and Increased Self-Efficacy
阅读精读
可阅读全文PAPER
PhotoMat: A Material Generator Learned from Single Flash Photos
阅读精读
可阅读全文PAPER
Photorealistic Material Editing Through Direct Image Manipulation
阅读精读
可阅读全文PAPER
pixelNeRF: Neural Radiance Fields from One or Few Images
阅读精读
可阅读全文PAPER
PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive Transformer
阅读精读
可阅读全文PAPER
PRL: Process Reward Learning Improves LLMs' Reasoning Ability and Broadens the Reasoning Boundary
阅读精读
可阅读全文PAPER
Procedural Material Generation with Reinforcement Learning
阅读精读
可阅读全文PAPER
ProcFunc: Function-Oriented Abstractions for Procedural 3D Generation in Python
阅读精读
可阅读全文PAPER
Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis
阅读精读
可阅读全文PAPER
RadarNet: Efficient Gesture Recognition Technique Utilizing a Miniature Radar Sensor
阅读精读
可阅读全文PAPER
ReCamMaster: Camera-Controlled Generative Rendering from A Single Video
阅读精读
可阅读全文PAPER
ReflectanceFusion: Diffusion-based text to SVBRDF Generation
阅读精读
可阅读全文PAPER
RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs
阅读精读
可阅读全文PAPER
Research contributions in human-computer interaction
阅读精读
可阅读全文PAPER
Residual path integrals for re-rendering
阅读精读
可阅读全文PAPER
Retrieval-Augmented Fine-Tuning With Preference Optimization For Visual Program Generation
阅读精读
可阅读全文PAPER
ReVideo: Remake a Video with Motion and Content Control
阅读精读
可阅读全文PAPER
RGB↔X: Image Decomposition and Synthesis Using Material- and Lighting-Aware Diffusion Models
阅读精读
可阅读全文PAPER
Scalable Diffusion Models with Transformers
阅读精读
可阅读全文PAPER
Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation
阅读精读
可阅读全文PAPER
Score-Based Generative Modeling through Stochastic Differential Equations
阅读精读
可阅读全文PAPER
ShaderAgent: Self-Evolving Agentic Procedural Material Generation
阅读精读
可阅读全文PAPER
Sketch-based interaction and modeling: where do we stand?
阅读精读
可阅读全文PAPER
Sketch-based modeling: A survey
阅读精读
可阅读全文PAPER
Sketch2CAD: Sequential CAD Modeling by Sketching in Context
阅读精读
可阅读全文PAPER
StableMaterials: Enhancing Diversity in Material Generation via Semi-Supervised Learning
阅读精读
可阅读全文PAPER
StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On
阅读精读
可阅读全文PAPER
Still-Moving: Customized Video Generation without Customized Video Data
阅读精读
可阅读全文PAPER
SurfaceNet: Adversarial SVBRDF Estimation from a Single Image
阅读精读
可阅读全文PAPER
Symmetry-driven 3D Reconstruction from Concept Sketches
阅读精读
可阅读全文PAPER
TexSliders: Diffusion-Based Texture Editing in CLIP Space
阅读精读
可阅读全文PAPER
TexTile: A Differentiable Metric for Texture Tileability
阅读精读
可阅读全文PAPER
Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On
阅读精读
可阅读全文PAPER
TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion
阅读精读
可阅读全文PAPER
The Model Human Processor: An Engineering Model of Human Performance
阅读精读
可阅读全文PAPER
threestudio: a modular framework for diffusion-guided 3D generation
阅读精读
可阅读全文PAPER
TokenVerse: Versatile Multi-concept Personalization in Token Modulation Space
阅读精读
可阅读全文PAPER
Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing
阅读精读
可阅读全文PAPER
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
阅读精读
可阅读全文PAPER
UltraZoom: Generating Gigapixel Images from Regular Photos
阅读精读
可阅读全文PAPER
Understanding Diffusion Models: A Unified Perspective
阅读精读
可阅读全文PAPER
Usability Evaluation Considered Harmful (Some of the Time)
阅读精读
可阅读全文PAPER
Video Diffusion Models
阅读精读
可阅读全文PAPER
VideoComposer: Compositional Video Synthesis with Motion Controllability
阅读精读
可阅读全文PAPER
VideoControlNet: A Motion-Guided Video-to-Video Translation Framework by Using Diffusion Model with ControlNet
阅读精读
可阅读全文PAPER
VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondence
阅读精读
可阅读全文PAPER
VisualPRM: An Effective Process Reward Model for Multimodal Reasoning
阅读精读
可阅读全文PAPER
VLMaterial: Procedural Material Generation with Large Vision-Language Models
阅读精读
可阅读全文PAPER
What Do Hackathons Do? Understanding Participation in Hackathons Through Program Theory Analysis
阅读精读
可阅读全文PAPER
Zero-1-to-3: Zero-shot One Image to 3D Object
阅读精读
可阅读全文PAPER
Zero-shot Image-to-Image Translation
阅读精读
可阅读全文PAPER
Zero-Shot Text-Guided Object Generation with Dream Fields
阅读精读
可阅读全文PAPER
ZeST: Zero-Shot Material Transfer from a Single Image
阅读精读
可阅读全文COLLECTION
Aspire｜从模糊目标到可保留能力的自进化
阅读精读
可阅读全文COLLECTION
BlenderGym｜论文精读与 PMG Benchmark 设计
阅读精读
可阅读全文COLLECTION
BlenderGym 精读与 PMG Benchmark 设计
阅读精读
可阅读全文COLLECTION
DuetSVG
阅读精读
可阅读全文COLLECTION
HarnessDev｜LLM 能否创建并迭代自己的 Agent Harness？
阅读精读
可阅读全文COLLECTION
MaterialApprentice｜深度论文精读
阅读精读
可阅读全文COLLECTION
ReAct × Reflexion｜对照式深度精读
阅读精读
可阅读全文COLLECTION
S³Gym｜深度论文精读
阅读精读
可阅读全文COLLECTION
Scene Graph Thinking · 深度论文精读
阅读精读
可阅读全文COLLECTION
Vision2Web · 从视觉复刻到全栈验证｜Benchmark 深度精读
阅读精读
可阅读全文COLLECTION
Visual Sketchpad｜深度论文精读
阅读精读
可阅读全文PAPER
Raven: The Harness of Harnesses for Composable Agentic Intelligence
阅读精读
可阅读全文PAPER
MaLiang-Harness: A Programmable Path to Image and Video Generation
阅读精读
可阅读全文PAPER
MatLoom · 把材质的构造规则一起生成 | Paper Reading
阅读精读
没有找到匹配的论文试试更短的关键词，或重置筛选。