|
arxiv.org
|
<div class="publication-title">Click2Insert: Video Object Insertion via Sparse Click
Guidance</div>
|
|
arxiv.org
|
Paper
|
|
arxiv.org
|
<div class="publication-title">Reward-Aware Trajectory Shaping for Few-step Visual Generation
</div>
|
|
arxiv.org
|
Paper
|
|
telephysics.github.io
|
<div class="publication-title">PhysOmni: Physics-Grounded Multi-Object Scene Generation from
a Single Image with Real-Time Interaction</div>
|
|
telephysics.github.io
|
Project
|
|
arxiv.org
|
Paper
|
|
arxiv.org
|
<div class="publication-title">Learning to Credit the Right Steps: Objective-aware Process
Optimization for Visual Generation</div>
|
|
arxiv.org
|
Paper
|
|
arxiv.org
|
<div class="publication-title">Rethinking Reward Signals in Video GRPO: When Scores Become Targets</div>
|
|
arxiv.org
|
<div class="publication-title">SIFT: Self-Imagination Fine-Tuning for Physically Plausible Motion in Video Diffusion Models</div>
|
|
arxiv.org
|
<div class="publication-title">Seeing What Matters: Visual Preference Policy Optimization
for
Visual Generation
</div>
|
|
arxiv.org
|
<div class="publication-title">Learning What to Trust: Bayesian Prior-Guided Optimization
for
Visual Generation
</div>
|
|
scottykma.github.io
|
<div class="publication-title">TempoMaster: Efficient
Long Video Generation via Next-Frame-Rate Prediction
</div>
|
|
magref-video.github.io
|
<div class="publication-title">MAGREF: Masked Guidance for Any-Reference Video Generation
</div>
|
|
arxiv.org
|
<div class="publication-title">Hierarchical Neural Semantic Representation for 3D Semantic
Correspondence</div>
|
|
ip-prompter.github.io
|
<div class="publication-title">IP-Prompter: Training-Free Theme-Specific Image Generation
via
Dynamic Visual Prompting</div>
|
|
arxiv.org
|
<div class="publication-title">DeTeCtive: Detecting AI-generated Text via Multi-Level
Contrastive Learning</div>
|
|
arxiv.org
|
<div class="publication-title">You Only Look Around: Learning Illumination-Invariant Feature
for
Low-light Object Detection</div>
|
|
unihair24.github.io
|
<div class="publication-title">Towards Unified 3D Hair Reconstruction from Single-View
Portraits
</div>
|
|
sisidai.github.io
|
<div class="publication-title">InterFusion: Text-Driven Generation of 3D Human-Object
Interaction</div>
|
|
direct-a-video.github.io
|
<div class="publication-title">Direct-a-Video: Customized Video Generation with
User-Directed
Camera Movement and Object Motion</div>
|
|
i2v-adapter-paper.github.io
|
<div class="publication-title">I2V-Adapter: A General Image-to-Video Adapter for Diffusion
Models</div>
|
|
vcc.tech
|
<div class="publication-title">Spatial and Surface Correspondence Field for Interaction
Transfer
</div>
|
|
vrmm-paper.github.io
|
<div class="publication-title">VRMM: A Volumetric Relightable Morphable Head Model</div>
|
|
arxiv.org
|
<div class="publication-title">LGTM: Local-to-Global Text-Driven Human Motion Diffusion
Model
</div>
|
|
arxiv.org
|
<div class="publication-title">DiffStyler: Controllable Dual Diffusion for Text-Driven Image
Stylization</div>
|
|
mmfs-paper.github.io
|
<div class="publication-title">Multi-Modal Face Stylization with a Generative Prior</div>
|
|
travatar-paper.github.io
|
<div class="publication-title">Towards Practical Capture of High-Fidelity Relightable
Avatars
</div>
|
|
arxiv.org
|
<div class="publication-title">3D Keypoint Estimation using Implicit Representation Learning
</div>
|
|
arxiv.org
|
<div class="publication-title">A Unified Arbitrary Style Transfer Framework via Adaptive
Contrastive Learning</div>
|
|
paulyzheng.github.io
|
<div class="publication-title">HairStep: Transfer Synthetic to Real Using Strand and Depth
Maps
for Single-View 3D Hair Modeling</div>
|
|
arxiv.org
|
<div class="publication-title">Semi-Weakly Supervised Object Kinematic Motion Prediction
</div>
|
|
arxiv.org
|
<div class="publication-title">Inversion-Based Style Transfer with Diffusion Models</div>
|
|
equi-articulated-pose.github.io
|
<div class="publication-title">Self-Supervised Category-Level Articulated Object Pose
Estimation
with Part-Level SE(3) Equivariance</div>
|
|
arxiv.org
|
<div class="publication-title">LitAR: Visually Coherent Lighting for Mobile Augmented
Reality
</div>
|
|
arxiv.org
|
<div class="publication-title">Domain Enhanced Arbitrary Image Style Transfer via
Contrastive
Learning</div>
|
|
arxiv.org
|
<div class="publication-title">Deep Constrained Least Squares for Blind Image
Super-Resolution
</div>
|
|
arxiv.org
|
<div class="publication-title">Task-Aware Sampling Layer for Point-Wise Analysis</div>
|
|
arxiv.org
|
<div class="publication-title">HPNet: Deep Primitive Segmentation Using Hybrid
Representations
</div>
|
|
arxiv.org
|
<div class="publication-title">Scene Synthesis via Uncertainty-Driven Attribute
Synchronization
</div>
|
|
arxiv.org
|
<div class="publication-title">FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose
Estimation</div>
|
|
arxiv.org
|
<div class="publication-title">NBNet: Noise Basis Learning for Image Denoising with Subspace
Projection</div>
|
|
arxiv.org
|
<div class="publication-title">Arbitrary Video Style Transfer via Multi-Channel Correlation
</div>
|
|
arxiv.org
|
<div class="publication-title">Practical Deep Raw Image Denoising on Mobile Devices</div>
|
|
arxiv.org
|
<div class="publication-title">FPConv: Learning Local Flattening for Point Convolution</div>
|
|
arxiv.org
|
<div class="publication-title">PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF
Pose Estimation</div>
|
|
arxiv.org
|
<div class="publication-title">Disentangled Image Matting</div>
|
|
arxiv.org
|
<div class="publication-title">Semi-supervised Skin Detection by Network with Mutual
Guidance
</div>
|
|
arxiv.org
|
<div class="publication-title">GIF2Video: Color Dequantization and Temporal Interpolation of
GIF
images</div>
|
|
arxiv.org
|
<div class="publication-title">Video Inpainting by Jointly Learning Temporal Structure and
Spatial Details</div>
|
|
happylun.github.io
|
<div class="publication-title">Learning to Group Discrete Graphical Patterns</div>
|
|
arxiv.org
|
<div class="publication-title">High Resolution Shape Completion Using Deep Neural Networks
for
Global Structure and Local Geometry Inference</div>
|
|
liyiwei.org
|
<div class="publication-title">Point Sampling with General Noise Spectrum</div>
|
