CVPR 2025 Papers

Test-time adaptation using vision-language models (such as CLIP) to quickly adjust to distributional shifts of downstream tasks has shown great potential. Despite significant progress, existing methods are still limited to single-task test-time adaptation scenarios and have not effectively explored the issue of multi-task adaptation. To address this practical problem, we propose a novel Hierarchical Knowledge Prompt Tuning (HKPT) method, which achieves joint adaptation to multiple target domains by mining more comprehensive source domain discriminative knowledge and hierarchically modeling task-specific and task-shared knowledge. Specifically, HKPT constructs a CLIP prompt distillation framework that utilizes the broader source domain knowledge of large teacher CLIP to guide prompt tuning for lightweight student CLIP from multiple views during testing. Meanwhile, HKPT establishes task-specific dual dynamic knowledge graph to capture fine-grained contextual knowledge from continuous test data. To fully exploit the complementarity among multiple target tasks, HKPT employs an adaptive task grouping strategy for achieving inter-task knowledge sharing. Furthermore, HKPT can seamlessly transfer to basic single-task test-time adaptation scenarios while maintaining robust performance. Extensive experimental results in both multi-task and single-task test-time adaptation settings demonstrate that our HKPT significantly outperforms state-of-the-art methods.

3D content creation has achieved significant progress in terms of both quality and speed. Although current Gaussian Splatting-based methods can produce 3D objects within seconds, they are still limited by complex preprocessing or low controllability. In this paper, we introduce a novel framework designed to efficiently and controllably generate high-resolution 3D models from text promptsor image. Our key insights are three-fold: 1) Hierarchical Gaussian Mixture Model Splatting: We propose an hybrid hierarchical representation to extract fixed number of fine-grained Gaussians with multiscale details from textured object, also establish part-level representation of Gaussians primitives. 2) Mamba with adaptive tree topology: We present a diffusion mamba with tree-topology to adaptively generate Gaussians with disordered spatial structures, without the need for complex preprocessing and maintain linear complexity generation. 3) Controllable Generation: Building on the HGMM tree, we introduce a cascaded diffusion framework combining controllable implicit latent generation, which progressively generates condition-driven latents, and explicit splatting generation, which transforms latents into high-quality Gaussian primitives. Extensive experiments demonstrate the high fidelity and efficiency of our approach.

Most recent diffusion-based methods still show a large gap compared to non-diffusion methods for video frame interpolation, in both accuracy and efficiency. Most of them formulate the problem as a denoising procedure in latent space directly, which is less effective caused by the large latent space. We propose to model bilateral optical flow explicitly by hierarchical diffusion models, which has much smaller search space in the denoising procedure. Based on the flow diffusion model, we then use a flow-guided image synthesizer to produce the final result. We train the flow diffusion model and the image synthesizer end to end. Our method achieves state of the art in accuracy, and 10+ times faster than other diffusion-based methods. The project page is at: https://hfd-interpolation.github.io.

Dataset distillation is an emerging dataset reduction method, which condenses large-scale datasets while maintaining task accuracy. Current parameterization methods achieve enhanced performance under extremely high compression ratio by optimizing determined synthetic dataset in informative feature domain. However, they limit themselves to a fixed optimization space for distillation, neglecting the diverse guidance across different informative latent spaces. To overcome this limitation, we propose a novel parameterization method dubbed Hierarchical Parameterization Distillation (H-PD), to systematically explore hierarchical feature within provided feature space (e.g., layers within pre-trained generative adversarial networks). We verify the correctness of our insights by applying the hierarchical optimization strategy on GAN-based parameterization method. In addition, we introduce a novel class-relevant feature distance metric to alleviate the computational burden associated with synthetic dataset evaluation, bridging the gap between synthetic and original datasets. Experimental results demonstrate that the proposed H-PD achieves a significant performance improvement under various settings with equivalent time consumption, and even surpasses current generative distillation using diffusion models under extreme compression ratios IPC=1 and IPC=10.

We propose the Compact Clustering Attention (COCA) layer, an effective building block that introduces a hierarchical strategy for object-centric representation learning, while solving the unsupervised object discovery task on single images. COCA is an attention-based clustering module capable of extracting object-centric representations from multi-object scenes, when cascaded into a bottom-up hierarchical network architecture, referred to as COCA-Net. At its core, COCA utilizes a novel clustering algorithm that leverages the physical concept of compactness, to highlight distinct object centroids in a scene, providing a spatial inductive bias. Thanks to this strategy, COCA-Net generates high-quality segmentation masks on both the decoder side and, notably, the encoder side of its pipeline. Additionally, COCA-Net is not bound by a predetermined number of object masks that it generates and handles the segmentation of background elements better than its competitors. We demonstrate COCA-Net's segmentation performance on six widely adopted datasets, achieving superior or competitive results against the state-of-the-art models across nine different evaluation metrics.

Despite significant advances in the field of specular highlight removal in recent years, existing methods predominantly focus on natural images, where highlights typically appear on raised or edged surfaces of objects. These highlights are often small and sparsely distributed. However, for text images such as cards and posters, the flat surfaces reflect light uniformly, resulting in large areas of highlights. Current methods struggle with these large-area highlights in text images, often producing severe visual artifacts or noticeable discrepancies between filled pixels and the original image in the central high-intensity highlight areas. To address these challenges, we propose the Hierarchical Adaptive Filtering Network (HAFNet). Our approach performs filtering at both the downsampled deep feature layer and the upsampled image reconstruction layer. By designing and applying the Adaptive Comprehensive Filtering Module (ACFM) and Adaptive Dilated Filtering Module (ADFM) at different layers, our method effectively restores semantic information in large-area specular highlight regions and recovers detail loss at various scales. The required filtering kernels are pre-generated by a prediction network, allowing them to adaptively adjust according to different images and their semantic content, enabling robust performance across diverse scenarios. Additionally, we utilize Unity3D to construct a comprehensive large-area highlight dataset featuring images with rich texts and complex textures. Experimental results on various datasets demonstrate that our method outperforms state-of-the-art approaches.

Despite advancements in multimodal large language models (MLLMs), current approaches struggle in medium-to-long video understanding due to frame and context length limitations. As a result, these models often depend on frame sampling, which risks missing key information over time and lacks task-specific relevance. To address these challenges, we introduce **HierarQ**, a task-aware hierarchical Q-Former based framework that sequentially processes frames to bypass the need for frame sampling, while avoiding LLM's context length limitations. We introduce a lightweight two-stream language-guided feature modulator to incorporate task awareness in video understanding, with the entity stream capturing frame-level object information within a short context and the scene stream identifying their broader interactions over longer period of time. Each stream is supported by dedicated memory banks which enables our proposed **Hierar**chical **Q**uerying transformer (HierarQ) to effectively capture short and long-term context. Extensive evaluations on **10** video benchmarks across video understanding, question answering, and captioning tasks demonstrate HierarQ's state-of-the-art performance across most datasets, proving its robustness and efficiency for comprehensive video analysis. All code will be made available upon acceptance.

Hiding data using neural networks (i.e., neural steganography) has achieved remarkable success across both discriminative classifiers and generative adversarial networks. However, the potential of data hiding in diffusion models remains relatively unexplored. Current methods exhibit limitations in achieving high extraction accuracy, model fidelity, and hiding efficiency due primarily to the entanglement of the hiding and extraction processes with multiple denoising diffusion steps. To address these, we describe a simple yet effective approach that embeds images at specific timesteps in the reverse diffusion process by editing the learned score functions. Additionally, we introduce a parameter-efficient fine-tuning method that combines gradient-based parameter selection with low-rank adaptation to enhance model fidelity and hiding efficiency. Comprehensive experiments demonstrate that our method extracts high-quality images at human-indistinguishable levels, replicates the original model behaviors at both sample and population levels, and embeds images orders of magnitude faster than prior methods. Besides, our method naturally supports multi-recipient scenarios through independent extraction channels.

High-resolution image inputs allow Large Vision-Language Models (LVLMs) to capture finer visual details, improving comprehension. However, the increased training and computational costs associated with such inputs pose significant challenges. A common approach to mitigate these costs involves slicing the input into uniform patches using sliding windows, each aligned with the vision encoder's input size. While efficient, this method fragments the input, disrupting the continuity of context, which negatively impacts cross-patch perception tasks. To address these limitations, we propose HiRes-LLaVA, a novel framework designed to efficiently process high-resolution inputs of any size without altering the original contextual and geometric information. HiRes-LLaVA introduces two key components: (i) a SliceRestore Adapter (SRA) that reconstructs sliced patches into their original form, enabling efficient extraction of both global and local features through down-up-sampling and convolutional layers, and (ii) a Self-Mining Sampler (SMS) that compresses visual tokens based on internal relationships, preserving original context and positional information while reducing training overhead. To assess the ability of handling context fragmentation, we construct a new benchmark, EntityGrid-QA, consisting of edge-related tasks. Extensive experiments demonstrate the superiority of HiRes-LLaVA on both existing public benchmarks and EntityGrid-QA. For example, with SRA, our method achieves a performance improvement of 12% over state-of-the-art LVLMs in addressing fragmentation issues. Additionally, our SMS outperforms other visual token downsamplers, while offering high data efficiency.

Existing 2D-to-3D human pose estimation (HPE) methods struggle with the occlusion issue by enriching information like temporal and visual cues in the lifting stage. In this paper, we argue that these methods ignore the limitation of the sparse skeleton 2D input representation, which fundamentally restricts the 2D-to-3D lifting and worsens the occlusion issue. To address these, we propose a novel two-stage generative densification method, named Hierarchical Pose AutoRegressive Transformer (HiPART), to generate hierarchical 2D dense poses from the original sparse 2D pose. Specifically, we first develop a multi-scale skeleton tokenization module to quantize the highly dense 2D pose into hierarchical tokens and propose a skeleton-aware alignment to strengthen token connections. We then develop a hierarchical autoregressive modeling scheme for hierarchical 2D pose generation. With generated hierarchical poses as inputs for 2D-to-3D lifting, the proposed method shows strong robustness in occluded scenarios and achieves state-of-the-art performance on the single-frame-based 3D HPE. Moreover, it outperforms numerous multi-frame methods while reducing parameter and computational complexity and can also complement them to further enhance performance and robustness.

We present Hierarchical Motion Representation (HiMoR), a novel deformation representation for 3D Gaussian primitives capable of achieving high-quality monocular dynamic 3D reconstruction. The insight behind HiMoR is that motions in everyday scenes can be decomposed into coarser motions that serve as the foundation for finer details. Using a tree structure, HiMoR's nodes represent different levels of motion detail, with shallower nodes modeling coarse motion for temporal smoothness and deeper nodes capturing finer motion. Additionally, our model uses a few shared motion bases to represent motions of different sets of nodes, aligning with the assumption that motion tends to be smooth and simple. This motion representation design provides Gaussians with a more structured deformation, maximizing the use of temporal relationships to tackle the challenging task of monocular dynamic 3D reconstruction. We also propose using a more reliable perceptual metric as an alternative, given that pixel-level metrics for evaluating monocular dynamic 3D reconstruction can sometimes fail to accurately reflect the true quality of reconstruction. Extensive experiments demonstrate our method's efficacy in achieving superior novel view synthesis from challenging monocular videos with complex motions.

LiDAR point cloud semantic segmentation plays a crucial role in autonomous driving. In recent years, semi-supervised methods have gained popularity due to their significant reduction in annotation labor and time costs. Current semi-supervised methods typically focus on point cloud spatial distribution or consider short-term temporal representations, e.g., only two adjacent frames, often overlooking the rich long-term temporal properties inherent in autonomous driving scenarios. In driving experience, we observe that nearby objects, such as roads and vehicles, remain stable while driving, whereas distant objects exhibit greater variability in category and shape. This natural phenomenon is also captured by LiDAR, which reflects lower temporal sensitivity for nearby objects and higher sensitivity for distant ones. To leverage these characteristics, we propose HiLoTs, which learns high-temporal sensitivity and low-temporal sensitivity representations from continuous LiDAR frames. These representations are further enhanced and fused using a cross-attention mechanism. Additionally, we employ a teacher-student framework to align the representations learned by the labeled and unlabeled branches, effectively utilizing the large amounts of unlabeled data. Experimental results on the SemanticKITTI and nuScenes datasets demonstrate that our proposed HiLoTs outperforms state-of-the-art semi-supervised methods, and achieves performance close to LiDAR+Camera multimodal approaches.

Recent advancements in diffusion-based technologies have made significant strides, particularly in identity-preserved portrait generation (IPG). However, when using multiple reference images from the same ID, existing methods typically produce lower-fidelity portraits and struggle to customize face attributes precisely. To address these issues, this paper presents HiFi-Portrait, a high-fidelity method for zero-shot portrait generation. Specifically, we first introduce the face refiner and landmark generator to obtain fine-grained multi-face features and 3D-aware face landmarks. The landmarks include the reference ID and the target attributes. Then, we design HiFi-Net to fuse multi-face features and align them with landmarks, which improves ID fidelity and face control. In addition, we devise an automated pipeline to construct an ID-based dataset for training HiFi-Portrait. Extensive experimental results demonstrate that our method surpasses the SOTA approaches in face similarity and controllability. Furthermore, our method is also compatible with previous SDXL-based works.

Skeleton-based human action recognition has received widespread attention in recent years due to its diverse range of application scenarios. Due to the different sources of human skeletons, skeleton data naturally exhibit heterogeneity. The previous works, however, overlook the heterogeneity of human skeletons and solely construct models tailored for homogeneous skeletons. This work addresses the challenge of heterogeneous skeleton-based action representation learning, specifically focusing on processing skeleton data that varies in joint dimensions and topological structures. The proposed framework comprises two primary components: heterogeneous skeleton processing and unified representation learning. The former first converts two-dimensional skeleton data into three-dimensional skeleton via an auxiliary network, and then constructs a prompted unified skeleton using skeleton-specific prompts. We also design an additional modality named semantic motion encoding to harness the semantic information within skeletons. The latter module learns a unified action representation using a shared backbone network that processes different heterogeneous skeletons. Extensive experiments on the NTU-60, NTU-120, and PKU-MMD II datasets demonstrate the effectiveness of our method in various tasks of action understanding. Our approach can be applied to action recognition in robots with different humanoid structures.

We introduce a novel method for human shape and pose recovery that can fully leverage multiple static views. We target fixed-multiview people monitoring, including elderly care and safety monitoring, in which cameras can be installed at the corners of a room or an open space but whose configuration may vary depending on the environment. Our key idea is to formulate it as neural optimization. We achieve this with HeatFormer, a neural optimizer that iteratively refines the SMPL parameters given multiview images. HeatFormer realizes this SMPL parameter estimation as heatmap generation and alignment with a novel transformer encoder and decoder. Our formulation makes HeatFormer fundamentally agnostic to the number of cameras, their configuration, and calibration. We demonstrate the effectiveness of HeatFormer including its accuracy, robustness to occlusion, and generalizability through an extensive set of experiments. We believe HeatFormer can serve a key role in passive human behavior modeling.

We study the problem of making 3D scene reconstructions interactive by asking the following question: can we predict the sounds of human hands physically interacting with a scene? First, we record a video of a human manipulating objects within a 3D scene using their hands. We then use these action-sound pairs to train a rectified flow model to map 3D hand trajectories to their corresponding audio. At test time, a user can query the model for other actions, parameterized as sequences of hand poses, to estimate their corresponding sounds. In our experiments, we find that our generated sounds accurately convey material properties and actions, and that they are often indistinguishable to human observers from real sounds. Project page: https://www.yimingdou.com/hearing_hands/.

In mixed reality applications, a realistic acoustic experience in spatial environments is as crucial as the visual experience for achieving true immersion. Despite recent advances in neural approaches for Room Impulse Response (RIR) estimation, most existing methods are limited to the single environment on which they are trained, lacking the ability to generalize to new rooms with different geometries and surface materials. We aim to develop a unified model capable of reconstructing the spatial acoustic experience of any environment with minimum additional measurements. To this end, we present xRIR, a framework for cross-room RIR prediction. The core of our generalizable approach lies in combining a geometric feature extractor, which captures spatial context from panorama depth images, with a RIR encoder that extracts detailed acoustic features from only a few reference RIR samples. To evaluate our method, we introduce AcousticRooms, a new dataset featuring high-fidelity simulation of over 300,000 RIRs from 260 rooms. Experiments show that our method strongly outperforms a series of baselines. Furthermore, we successfully perform sim-to-real transfer by evaluating our model on four real-world environments, demonstrating the generalizability of our approach and the realism of our dataset.

Heuristic information for consensus set sampling is essential for correspondence-based point cloud registration, but existing approaches typically rely on supervised learning or expert-driven parameter tuning. In this work, we propose HeMoRa, a new unsupervised framework that trains a Heuristic information Generator (HeGen) to estimate sampling probabilities for correspondences using a Multi-order Reward Aggregator (MoRa) loss. The core of MoRa is to train HeGen through extensive trials and feedback, enabling unsupervised learning. While this process can be implemented using policy optimization, directly applying the policy gradient to optimize HeGen presents challenges such as sensitivity to noise and low reward efficiency. To address these issues, we propose a Maximal Reward Propagation (MRP) mechanism that enhances the training process by prioritizing noise-free signals and improving reward utilization. Experimental results show that equipped with HeMoRa, the consensus set sampler achieves improvements in both robustness and accuracy. For example, on the 3DMatch dataset with FCGF feature, the registration recall of our unsupervised methods (Ours+SM and Ours+SC^2) even outperforms the state-of-the-art supervised method VBreg. Our code is available at \href https://github.com/Laka-3DV/HeMoRa \texttt HeMoRa .

Currently, the demand for higher video quality has grown significantly. However, satellite video has low resolution, complex motion, and weak textures. Haze interference further exacerbates the loss of motion information and texture details, hindering effective spatiotemporal feature fusion and fine-grained feature mining. This presents significant challenges for subsequent super-resolution (SR) reconstruction, especially at continuous scales. To address these problems, this paper models the double-degradation process of hazy low-quality satellite videos and proposes a novel network to learn the optimal joint degradation pattern (ODPNet) for continuous-scale SR of hazy satellite videos. First, we design a prior-based feature soft dehazing module to eliminate haze interference at the feature level. Second, we develop a spatiotemporal self-attention (SSA) to capture long-range feature dependencies, thereby achieving effective spatiotemporal feature fusion. Third, we devise a tri-branch cross-aggregation block (TCB) to enhance feature representations of weak textures in satellite videos by effectively aggregating contextual information. Finally, we propose a cross-scale feature Top-k selection Transformer (CFTST), which aims to adaptively select and aggregate cross-scale latent codes to learn feature representations of satellite videos at arbitrary resolutions, thus enabling continuous-scale SR. Experiments show that ODPNet outperforms existing methods and achieves a better balance between model parameters and performance.