CVPR 2026 论文列表

Despite the advancements in diffusion-based image style transfer, existing methods are commonly limited by 1) semantic gap: the style reference could miss proper content semantics, causing uncontrollable stylization; 2) reliance on extra constraints (e.g., semantic masks) restricting applicability; 3) rigid feature associations lacking adaptive global-local alignment, failing to balance fine-grained stylization and global content preservation. These limitations, particularly the inability to flexibly leverage style inputs, fundamentally restrict style transfer in terms of personalization, accuracy, and adaptability.To address these, we propose StyleGallery, a training-free and semantic-aware framework that supports arbitrary reference images as input and enables effective personalized customization.It comprises three core stages: semantic region segmentation (adaptive clustering on latent diffusion features to divide regions without extra inputs); clustered region matching (block filtering on extracted features for precise alignment); and style transfer optimization (energy function-guided diffusion sampling with regional style loss to optimize stylization).Experiments on our introduced benchmark demonstrate that StyleGallery outperforms state-of-the-art methods in content structure preservation, regional stylization, interpretability, and personalized customization, particularly when leveraging multiple style references. The source code and dataset are available at https://github.com/iiiiiiiword/StyleGallery.

Self-supervised monocular depth estimation has achieved remarkable progress in recent years, yet frequency aliasing and the lack of fine-grained cross-frame motion modeling still lead to blurred depth boundaries and suboptimal camera motion estimation.To address these challenges, we propose a progressive self-supervised framework that integrates a Frequency-Guided Depth Network (FGDepth) and a PoseQuery Network (PQNet). FGDepth incorporates a plug-and-play Frequency-Guided Sampling module that explicitly enhances high-frequency details and suppresses aliasing artifacts, producing depth maps with sharper boundaries. PQNet employs channel-aligned attention to model fine-grained cross-frame motion features, enabling more accurate and robust camera motion estimation. Furthermore, we design a progressive three-stage decoupled training strategy that effectively leverages the complementarity between depth and pose estimation, further improving overall performance.Extensive experiments on the KITTI benchmark demonstrate state-of-the-art performance, achieving a 4.1% reduction in Sq Rel over strong baselines, and our method also exhibits excellent cross-dataset generalization on Make3D. Ablation studies further validate the effectiveness of each proposed component.

Cross-modal alignment aims to learn semantically consistent latent representations across diverse modalities. Prevailing methods rely on a text-guided aggregation paradigm to achieve fine-grained alignment, while they suffer from redundant patch-word correlations and high computational costs. To address these issues, we propose CoV-Align, an effective and efficient fine-grained cross-modal alignment framework with cohesive visual semantics priority. Through a semantically convergent attention mechanism, it progressively aggregates meaningful visual patches in a text-free manner. We design a coarse visual semantic feature extractor that integrates deformable attention and consistent assign attention to group patches with semantic consistency. A cohesive and discriminative feature optimization is presented to enhance intra-semantic cohesion and inter-semantic discriminability of visual region features, resulting in explicit improvements in cross-modal alignment. Extensive experiments demonstrate that CoV-Align achieves state-of-the-art performance on the Flickr30K and MS-COCO benchmarks. Notably, it delivers a 3-5xcomputational speedup compared to pioneer approaches, offering compelling advantages for large-scale multi-modal tasks.

Multimodal large language models (MLLMs) struggle with hallucinations, particularly with fine-grained queries, a challenge underrepresented by existing benchmarks that focus on coarse image-related questions. We introduce **FI**ne-grained **NE**gative que**R**ies (**FINER**), alongside two benchmarks: **FINER-CompreCap** and **FINER-DOCCI**. Using FINER, we analyze hallucinations across four settings: multi-object, multi-attribute, multi-relation, and "what" questions. Our benchmarks reveal that MLLMs hallucinate when fine-grained mismatches co-occur with genuinely present elements in the image. To address this, we propose **FINER-Tuning**, leveraging Direct Preference Optimization (DPO) on FINER-inspired data. Finetuning four frontier MLLMs with FINER-Tuning yields up to 24.2% gains (InternVL3.5-14B) on hallucinations from our benchmarks, while simultaneously improving performance on eight existing hallucination suites, and enhancing general multimodal capabilities across six benchmarks. Code, benchmark, and models are available at https://explainableml.github.io/finer-project/.

Learning with noisy labels (LNL) has received growing attention, with most prior work following the paradigm of clean-sample reliance (e.g., sample selection). However, this reliance also imposes intrinsic limitations, as overfitting to even a few noisy samples is inevitable, creating a major bottleneck for further improvement. This limitation motivates us to go beyond mere clean-sample reliance and explore how to actively forget corrupted knowledge already internalized by models while suppressing further noise assimilation. To this end, we propose FINE, a fundamentally novel perspective for LNL that unifies active ForgettIng via machine unlearning (MU) and Noise supprEssion via negative learning (NL) within a cohesive framework. Specifically, we first reveal two key stages of noise fitting: early-stage generalized learning and later-stage noise overfitting. To actively forget early-stage noise accumulation, we introduce an MU-based module that employs a negative cross-entropy loss to erase corrupted knowledge, while an NL-based module leveraging complementary labels suppresses later-stage overfitting and mitigates reliance on noisy supervision. These modules act synergistically as plug-and-play regularizers, seamlessly integrating into existing baselines. Finally, extensive experiments on both synthetic and real-world noisy benchmarks demonstrate that our FINE consistently boosts robustness and generalization.

Achieving spatial alignment between whole-slide images (WSIs) across stains is essential for integrating morphology and molecular information, yet it remains challenging due to extreme resolution, tissue fragmentation, and large nonlinear deformations. Conventional registration pipelines depend on global pre-alignment and spatial consistency, which often collapse under such distortions. We present SAR2Net, a framework that learns spatially anchored representations and reformulates cross-stain alignment as a region-level feature retrieval problem. Instead of estimating explicit transformations, SAR2Net learns pointwise representations encoding the relative spatial relationships to tissue landmarks. Given landmarks and arbitrary coordinates, it predicts spatially anchored features that serve as deformation-invariant descriptors of tissue topology. A two-stage retrieval framework then establishes correspondences between slides, even when global alignment is infeasible. Experiments on biopsy-oriented HE-IHC datasets show that SAR2Net achieves robust region-level alignment under severe tissue distortions, outperforming previous methods. Code is available at https://github.com/Shentl/SAR2Net

Scalable Vector Graphics (SVG) are central to digital design due to their inherent scalability and editability. Despite significant advancements in content generation enabled by Visual Language Models (VLMs), existing text-to-SVG generation methods are limited by a core challenge: the autoregressive training process does not incorporate visual perception of the final rendered image, which fundamentally constrains generation quality. To address this limitation, we propose an Introspective SVG Generation Framework (IntroSVG). At its core, the framework instantiates a unified VLM that operates in a closed loop, assuming dual roles of both generator and critic. Specifically, through Supervised Fine-Tuning (SFT), the model learns to draft SVGs and to provide feedback on their rendered outputs; moreover, we systematically convert early-stage failures into high-quality error-correction training data, thereby enhancing model robustness. Subsequently, we leverage a high-capacity teacher VLM to construct a preference dataset and further align the generator's policy through Direct Preference Optimization (DPO). During inference, the optimized generator and critic operate collaboratively in an iterative "generate-review-refine" cycle, starting from imperfect intermediate drafts to autonomously improve output quality. Experimental results demonstrate that our method achieves state-of-the-art performance across several key evaluation metrics, generating SVGs with more complex structures, stronger semantic alignment, and greater editability. These results corroborate the effectiveness of incorporating explicit visual feedback into the generation loop.

Segmenting small lesions in medical images remains notoriously difficult. Most prior work tackles this challenge by either designing better architectures, loss functions, or data augmentation schemes; and collecting more labeled data. We take a different view, arguing that part of the problem lies in how the background is modeled. Common lesion segmentation collapses all non-lesion pixels into a single "background" class, ignoring the rich anatomical context in which lesions appear. In reality, the background is highly heterogeneous--composed of tissues, organs, and other structures that can now be labeled manually or inferred automatically using existing segmentation models.In this paper, we argue that training with fine-grained labels that sub-divide the background class, which we call BackSplit, is a simple yet powerful paradigm that can offer a significant performance boost without increasing inference costs. From an information theoretic standpoint, we prove that BackSplit increases the expected Fisher Information relative to conventional binary training, leading to tighter asymptotic bounds and more stable optimization. With extensive experiments across multiple datasets and architectures, we empirically show that BackSplit consistently boosts small-lesion segmentation performance, even when auxiliary labels are generated automatically using pretrained segmentation models. Additionally, we demonstrate that auxiliary labels derived from interactive segmentation frameworks exhibit the same beneficial effect, demonstrating its robustness, simplicity, and broad applicability.

Flicker artifacts, arising from unstable illumination and row-wise exposure inconsistencies, pose a significant challenge in short-exposure photography, severely degrading image quality. Unlike typical artifacts, e.g., noise and low-light, flicker is a structured degradation with specific spatial-temporal patterns, which are not accounted for in current generic restoration frameworks, leading to suboptimal flicker suppression and ghosting artifacts. In this work, we reveal that flicker artifacts exhibit two intrinsic characteristics, periodicity and directionality, and propose Flickerformer, a transformer-based architecture that effectively removes flicker without introducing ghosting. Specifically, Flickerformer comprises three key components: a phase-based fusion module (PFM), an autocorrelation feed-forward network (AFFN), and a wavelet-based directional attention module (WDAM). Based on the periodicity, PFM performs inter-frame phase correlation to adaptively aggregate burst features, while AFFN exploits intra-frame structural regularities through autocorrelation, jointly enhancing the network's ability to perceive spatially recurring patterns. Moreover, motivated by the directionality of flicker artifacts, WDAM leverages high-frequency variations in the wavelet domain to guide the restoration of low-frequency dark regions, yielding precise localization of flicker artifacts. Extensive experiments demonstrate that Flickerformer outperforms state-of-the-art approaches in both quantitative metrics and visual quality. The source code is available at https://github.com/qulishen/Flickerformer.

We present FHAvatar, a novel framework for reconstructing 3D Gaussian avatars with composable face and hair components from an arbitrary number of views. Unlike previous approaches that couple facial and hair representations within a unified modeling process, we explicitly decouple two components in texture space by representing the face with planar Gaussians and the hair with strand-based Gaussians. To overcome the limitations of existing methods that rely on dense multi-view captures or costly per-identity optimization, we propose an aggregated transformer backbone to learn geometry-aware cross-view priors and head-hair structural coherence from multi-view datasets, enabling effective and efficient feature extraction and fusion from few casual captures. Extensive quantitative and qualitative experiments demonstrate that FHAvatar achieves state-of-the-art reconstruction quality from only a few observations of new identities within minutes, while supporting real-time animation, convenient hairstyle transfer, and stylized editing, broadening the accessibility and applicability of digital avatar creation.

Recent advancements in computer vision have accelerated the development of autonomous driving. Despite these advancements, training machines to drive in a way that aligns with human expectations remains a significant challenge. Human factors are still essential, as humans possess a sophisticated cognitive system capable of rapidly interpreting scene information and making accurate decisions. Aligning machine with human intent has been explored with Reinforcement Learning with Human Feedback (RLHF). Conventional RLHF methods rely on collecting human preference data by manually ranking AI-generated outputs, which is time-consuming and indirect. In this work, we propose an electroencephalography (EEG)-guided decision-making framework to incorporate human cognitive insights into reinforcement learning (RL) for autonomous driving. We collected EEG signals from 20 participants in a realistic driving simulator and analyzed event-related potentials (ERP) in response to sudden environmental changes. Our proposed framework employs a neural network to predict the strength of ERP based on the cognitive information from visual scene information. Moreover, we explore the integration of such cognitive information into the reward signal of the RL algorithm. Experimental results show that our framework can improve the collision avoidance ability of the RL algorithm, highlighting the potential of neuro-cognitive feedback in enhancing autonomous driving systems.

Reward models (RMs) are inherently non-neutral value functions designed and trained to encode specific objectives, such as human preferences or text-image alignment. RMs have become crucial components of text-to-image (T2I) generation systems where they are used at various stages for dataset filtering, as evaluation metrics, as a supervisory signal during optimization of parameters, and for post-generation safety and quality filtering of T2I outputs. While specific problems with the integration of RMs into the T2I pipeline have been studied (e.g. reward hacking or mode collapse), their robustness and fairness as scoring functions remains largely unknown. We conduct a large scale audit of RM robustness with respect to demographic biases during T2I model training and generation. We provide quantitative and qualitative evidence that while originally developed as quality measures, RMs encode demographic biases, which cause reward-guided optimization to disproportionately sexualize female image subjects, reinforce gender/racial stereotypes, and collapse demographic diversity. These findings highlight shortcomings in current reward models, challenge their reliability as quality metrics, and underscore the need for improved data collection and training procedures to enable more robust scoring.

With the widespread adoption of deep learning in visual tasks, Class-Incremental Learning (CIL) has become an important paradigm for handling dynamically evolving data distributions. However, CIL faces the core challenge of *catastrophic forgetting*, often manifested as a prediction bias toward new classes. Existing methods mainly attribute this bias to intra-task class imbalance and focus on corrections at the classifier head. In this paper, we highlight an overlooked factor--*temporal imbalance*--as a key cause of this bias. Earlier classes receive stronger negative supervision toward the end of training, leading to asymmetric precision and recall. We establish a temporal supervision model, formally define temporal imbalance, and propose the Temporal-Adjusted Loss (TAL), which uses a temporal decay kernel to construct a supervision strength vector and dynamically reweight the negative supervision in cross-entropy loss. Theoretical analysis shows that TAL degenerates to standard cross-entropy under balanced conditions and effectively mitigates prediction bias under imbalance. Extensive experiments demonstrate that TAL significantly reduces forgetting and improves performance on multiple CIL benchmarks, underscoring the importance of temporal modeling for stable long-term learning.

Despite recent advances in personalized image generation, existing models consistently fail to produce reliable multi-human scenes, often merging or losing facial identity. We present Ar2Can, a novel two-stage framework that disentangles spatial planning from identity rendering for multi-human generation. The Architect predicts structured layouts, specifying where each person should appear. The Artist then synthesizes photorealistic images, guided by a spatially-grounded face matching reward that combines Hungarian spatial alignment with identity similarity. This approach ensures faces are rendered at correct locations and faithfully preserve reference identities. We develop two Architect variants, seamlessly integrated with our diffusion-based Artist model. This is optimized via Group Relative Policy Optimization (GRPO) using compositional rewards for count accuracy, image quality, and identity matching. Evaluated on the MultiHuman-Testbench, Ar2Can achieves substantial improvements in both count accuracy and identity preservation, while maintaining high perceptual quality. Notably, our method achieves these results using primarily synthetic data, without requiring real multi-human images. Project page: https://qualcomm-ai-research.github.io/ar2can/

Sketch editing requires jointly handling high-level semantic changes and precise local redrawing, a combination that is particularly challenging for sparse, style-sensitive line art. Unlike natural images, sketches rely on minimal visual cues, making it difficult for existing methods to reconcile global semantic modifications with fine-grained structural control while preserving overall coherence. We present SketchAssist, an interactive sketch assistant that unifies instruction-guided editing with line-guided region redrawing, enabling efficient and controllable sketch manipulation while preserving overall composition. To support this task, we introduce a controllable data generation pipeline that constructs structured edit sequences with precise attribute variations and maintains structural alignment across multi-step modifications, while expanding stylistic diversity via style-preserving transformations. Building on this data, SketchAssist adopts a unified framework based on DiT, using a multi-channel input representation to encode sketches, masks, and guidance signals within a single interface. To further handle different editing modes, we integrate a Task-guided Mixture-of-Experts (T-MoE) into LoRA layers, enabling adaptive control over semantic and structural guidance. Extensive experiments demonstrate state-of-the-art performance on both tasks, achieving strong instruction adherence and improved structural and style consistency compared to recent methods. Together, our method provide a practical and controllable solution for sketch editing.

Recent advances in visuomotor policy learning have enabled robots to perform control directly from visual inputs. Yet, extending such end-to-end learning from single-arm to bimanual manipulation remains challenging due to the need for both independent perception and coordinated interaction between arms. Existing methods typically favor one side--either decoupling the two arms to avoid interference or enforcing strong cross-arm coupling for coordination--thus lacking a unified treatment. We propose CUBic, a Coordinated and Unified framework for Bimanual perception and control that reformulates bimanual coordination as a unified perceptual modeling problem. CUBic learns a shared tokenized representation bridging perception and control, where independence and coordination emerge intrinsically from structure rather than from hand-crafted coupling. Our approach integrates three components: unidirectional perception aggregation, bidirectional perception coordination through two codebooks with shared mapping, and a unified perception-to-control diffusion policy. Extensive experiments on the RoboTwin benchmark show that CUBic consistently surpasses standard baselines, achieving marked improvements in coordination accuracy and task success rates over state-of-the-art visuomotor baselines.

Denoising-based diffusion transformers, despite their strong generation performance, suffer from inefficient training convergence. Existing methods addressing this issue, such as REPA (relying on external representation encoders) or SRA (requiring dual-model setups), inevitably incur heavy computational overhead during training due to external dependencies. To tackle these challenges, this paper proposes SRA 2, a lightweight intrinsic self-representation alignment framework for efficient diffusion training. SRA 2 leverages off-the-shelf pre-trained Variational Autoencoder (VAE) features: their reconstruction property ensures inherent encoding of visual priors like rich texture details, structural patterns, and basic semantic information. Specifically, SRA 2 aligns the intermediate latent features of diffusion transformers with VAE features via a lightweight projection layer, supervised by a feature alignment loss. This design accelerates training without extra representation encoders or dual-model maintenance, resulting in a simple yet effective pipeline. Extensive experiments demonstrate that SRA 2 improves both generation quality and training convergence speed compared to vanilla diffusion transformers, matches or outperforms state-of-the-art acceleration methods, and incurs merely 4% extra GFLOPs with zero additional cost for external guidance models.

Reinforcement learning (RL) has demonstrated remarkable success in text and image generation, yet its potential in 3D generation remains largely unexplored. Existing attempts typically rely on offline direct preference optimization (DPO) method, which suffers from low training efficiency and limited generalization. In this work, we aim to enhance both the training efficiency and generation quality of RL in 3D mesh generation. Specifically, (1) we design the first asynchronous online RL framework tailored for 3D mesh generation post-training efficiency improvement, which is 3.75xfaster than synchronous RL. (2) We propose Advantage-guided Ranking Preference Optimization (ARPO), a novel RL algorithm that achieves a better trade-off between training efficiency and generalization than current RL algorithms designed for 3D mesh generation, such as DPO and group relative policy optimization (GRPO). (3) Based on asynchronous ARPO, we propose Mesh-Pro, which additionally introduces a novel diagonal-aware mixed triangular-quadrilateral tokenization for mesh representation and a ray-based reward for geometric integrity. Mesh-Pro achieves state-of-the-art performance on artistic and dense meshes.

Open-Vocabulary Temporal Action Detection (OV-TAD) aims to classify and localize action segments in untrimmed videos for unseen categories. Previous methods rely solely on global alignment between label-level semantics and visual features, which is insufficient to transfer temporal consistent visual knowledge from seen to unseen classes. To address this, we propose a Phase-wise Decomposition and Alignment (PDA) framework, which enables fine-grained action pattern learning for effective prior knowledge transfer. Specifically, we first introduce the CoT-Prompting Semantic Decomposition (CSD) module, which leverages the chain-of-thought (CoT) reasoning ability of large language models to automatically decompose action labels into coherent phase-level descriptions, emulating human cognitive processes. Then, Text-infused Foreground Filtering (TIF) module is introduced to adaptively filter action-relevant segments for each phase leveraging phase-wise semantic cues, producing semantically aligned visual representations. Furthermore, we propose the Adaptive Phase-wise Alignment (APA) module to perform phase-level visual-textual matching, and adaptively aggregates alignment results across phases for final prediction. This adaptive phase-wise alignment facilitates the capture of transferable action patterns and significantly enhances generalization to unseen actions. Extensive experiments on two OV-TAD benchmarks demonstrated the superiority of the proposed method.