Paper-Conference | Hugo Academic CV Themehttps://cvl-uestc.github.io/publication_types/paper-conference/Paper-ConferenceHugo Blox Builder (https://hugoblox.com)en-usSun, 01 Mar 2026 00:00:00 +0000https://cvl-uestc.github.io/media/logo_hu_91122116bb3ed5f7.pngPaper-Conferencehttps://cvl-uestc.github.io/publication_types/paper-conference/πŸ‘‘ CVPR 2026 | Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compressionhttps://cvl-uestc.github.io/publications/paper2026/dvq/Sun, 01 Mar 2026 00:00:00 +0000https://cvl-uestc.github.io/publications/paper2026/dvq/πŸ‘‘ CVPR 2026 | Guiding a Diffusion Transformer with the Internal Dynamics of Itselfhttps://cvl-uestc.github.io/publications/paper2026/ig/Sun, 01 Mar 2026 00:00:00 +0000https://cvl-uestc.github.io/publications/paper2026/ig/πŸ‘‘ CVPR 2026 | IDESplat: Iterative Depth Probability Estimation for Generalizable 3D Gaussian Splattinghttps://cvl-uestc.github.io/publications/paper2026/ide-splat/Sun, 01 Mar 2026 00:00:00 +0000https://cvl-uestc.github.io/publications/paper2026/ide-splat/πŸ‘‘ CVPR 2026 | Taming Sampling Perturbations with Variance Expansion Loss for Latent Diffusion Modelshttps://cvl-uestc.github.io/publications/paper2026/ve-loss/Sun, 01 Mar 2026 00:00:00 +0000https://cvl-uestc.github.io/publications/paper2026/ve-loss/πŸŽ‰ ICLR 2026 | MVAR: Visual Autoregressive Modeling with Scale and Spatial Markovian Conditioninghttps://cvl-uestc.github.io/publications/paper2026/mvar/Wed, 01 Oct 2025 00:00:00 +0000https://cvl-uestc.github.io/publications/paper2026/mvar/πŸŽ‰ ICLR 2026 | Texture Vector-Quantization and Reconstruction Aware Prediction for Generative Super-Resolutionhttps://cvl-uestc.github.io/publications/paper2026/tvq-rap/Wed, 01 Oct 2025 00:00:00 +0000https://cvl-uestc.github.io/publications/paper2026/tvq-rap/πŸ† ICCV 2025 | Consistency Trajectory Matching for One-Step Generative Super-Resolutionhttps://cvl-uestc.github.io/publications/paper2025/ctmsr/Wed, 01 Oct 2025 00:00:00 +0000https://cvl-uestc.github.io/publications/paper2025/ctmsr/πŸ† ICCV 2025 | Learning Pixel-adaptive Multi-layer Perceptrons for Real-time Image Enhancementhttps://cvl-uestc.github.io/publications/paper2025/bpam/Wed, 01 Oct 2025 00:00:00 +0000https://cvl-uestc.github.io/publications/paper2025/bpam/πŸ† ICCV 2025 | PerLDiff：Controllable Street View Synthesis Using Perspective-Layout Diffusion Modelshttps://cvl-uestc.github.io/publications/paper2025/perldiff/Wed, 01 Oct 2025 00:00:00 +0000https://cvl-uestc.github.io/publications/paper2025/perldiff/πŸ† ICCVW 2025 | HiLLIE: Human-in-the-Loop Training for Low-Light Image Enhancementhttps://cvl-uestc.github.io/publications/paper2025/hillie/Wed, 01 Oct 2025 00:00:00 +0000https://cvl-uestc.github.io/publications/paper2025/hillie/πŸ‘‘ CVPR 2026 | Task-Aware Image Signal Processor for Advanced Visual Perceptionhttps://cvl-uestc.github.io/publications/paper2026/ta-isp/Wed, 01 Oct 2025 00:00:00 +0000https://cvl-uestc.github.io/publications/paper2026/ta-isp/Generative Image Compression by Estimating Gradients of the Rate-variable Feature Distributionhttps://cvl-uestc.github.io/publications/preprints/vcd/Wed, 01 Oct 2025 00:00:00 +0000https://cvl-uestc.github.io/publications/preprints/vcd/LRTI-VSR: Learning Long-Range Refocused Temporal Information from Short Video Clipshttps://cvl-uestc.github.io/publications/preprints/lrti-vsr/Wed, 01 Oct 2025 00:00:00 +0000https://cvl-uestc.github.io/publications/preprints/lrti-vsr/Neural Stereo Video Compression with Hybrid Disparity Compensationhttps://cvl-uestc.github.io/publications/preprints/hdc-svc/Wed, 01 Oct 2025 00:00:00 +0000https://cvl-uestc.github.io/publications/preprints/hdc-svc/πŸ‘‘ CVPR 2025 | Learned Image Compression with Dictionary-based Entropy Modelhttps://cvl-uestc.github.io/publications/paper2025/dcae/Sun, 01 Jun 2025 00:00:00 +0000https://cvl-uestc.github.io/publications/paper2025/dcae/<!-- > [!NOTE] > Click the _Cite_ button above to demo the feature to enable visitors to import publication metadata into their reference management software. > [!NOTE] > Create your slides in Markdown - click the _Slides_ button to check out the example. Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/). -->πŸ‘‘ CVPR 2025 | Progressive Focused Transformer for Single Image Super-Resolutionhttps://cvl-uestc.github.io/publications/paper2025/pft/Sun, 01 Jun 2025 00:00:00 +0000https://cvl-uestc.github.io/publications/paper2025/pft/πŸ‘‘ CVPR 2025 | Uncertainty-guided Perturbation for Image Super-Resolution Diffusion Modelhttps://cvl-uestc.github.io/publications/paper2025/upsr/Sun, 01 Jun 2025 00:00:00 +0000https://cvl-uestc.github.io/publications/paper2025/upsr/⭐ NeurIPS 2024 | Causal Context Adjustment Loss for Learned Image Compressionhttps://cvl-uestc.github.io/publications/paper2024/cca/Sun, 01 Dec 2024 00:00:00 +0000https://cvl-uestc.github.io/publications/paper2024/cca/<!-- > [!NOTE] > Click the _Cite_ button above to demo the feature to enable visitors to import publication metadata into their reference management software. > [!NOTE] > Create your slides in Markdown - click the _Slides_ button to check out the example. Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/). -->πŸ”₯ ICML 2025 | Inductive Gradient Adjustment For Spectral Bias In Implicit Neural Representationshttps://cvl-uestc.github.io/publications/paper2025/iga-inr/Sun, 01 Dec 2024 00:00:00 +0000https://cvl-uestc.github.io/publications/paper2025/iga-inr/<!-- > [!NOTE] > Click the _Cite_ button above to demo the feature to enable visitors to import publication metadata into their reference management software. > [!NOTE] > Create your slides in Markdown - click the _Slides_ button to check out the example. Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/). -->πŸ‘‘ CVPR 2024 | Improved Implicit Neural Representation with Fourier Reparameterized Traininghttps://cvl-uestc.github.io/publications/paper2024/fr-inr/Sat, 01 Jun 2024 00:00:00 +0000https://cvl-uestc.github.io/publications/paper2024/fr-inr/<!-- > [!NOTE] > Click the _Cite_ button above to demo the feature to enable visitors to import publication metadata into their reference management software. > [!NOTE] > Create your slides in Markdown - click the _Slides_ button to check out the example. Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/). -->πŸ‘‘ CVPR 2024 | Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionaryhttps://cvl-uestc.github.io/publications/paper2024/atd/Sat, 01 Jun 2024 00:00:00 +0000https://cvl-uestc.github.io/publications/paper2024/atd/<!-- > [!NOTE] > Click the _Cite_ button above to demo the feature to enable visitors to import publication metadata into their reference management software. > [!NOTE] > Create your slides in Markdown - click the _Slides_ button to check out the example. Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/). -->πŸ‘‘ CVPR 2024 | Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attentionhttps://cvl-uestc.github.io/publications/paper2024/mia-vsr/Sat, 01 Jun 2024 00:00:00 +0000https://cvl-uestc.github.io/publications/paper2024/mia-vsr/<!-- > [!NOTE] > Click the _Cite_ button above to demo the feature to enable visitors to import publication metadata into their reference management software. > [!NOTE] > Create your slides in Markdown - click the _Slides_ button to check out the example. Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/). -->