Songcen Xu

Zhihao Li, Jianzhuang Liu, Zhensong Zhang et al. · pku

Top-down methods dominate the field of 3D human pose and shape estimation, because they are decoupled from human detection and allow researchers to focus on the core problem. However, cropping, their first step, discards the location information from the very beginning, which makes themselves unable to accurately predict the global rotation in the original camera coordinate system. To address this problem, we propose to Carry Location Information in Full Frames (CLIFF) into this task. Specifically, we feed more holistic features to CLIFF by concatenating the cropped-image feature with its bounding box information. We calculate the 2D reprojection loss with a broader view of the full frame, taking a projection process similar to that of the person projected in the image. Fed and supervised by global-location-aware information, CLIFF directly predicts the global rotation along with more accurate articulated poses. Besides, we propose a pseudo-ground-truth annotator based on CLIFF, which provides high-quality 3D annotations for in-the-wild 2D datasets and offers crucial full supervision for regression-based methods. Extensive experiments on popular benchmarks show that CLIFF outperforms prior arts by a significant margin, and reaches the first place on the AGORA leaderboard (the SMPL-Algorithms track). The code and data are available at https://github.com/huawei-noah/noah-research/tree/master/CLIFF.

Sicheng Yang, Zilin Wang, Zhiyong Wu et al.

The automatic co-speech gesture generation draws much attention in computer animation. Previous works designed network structures on individual datasets, which resulted in a lack of data volume and generalizability across different motion capture standards. In addition, it is a challenging task due to the weak correlation between speech and gestures. To address these problems, we present UnifiedGesture, a novel diffusion model-based speech-driven gesture synthesis approach, trained on multiple gesture datasets with different skeletons. Specifically, we first present a retargeting network to learn latent homeomorphic graphs for different motion capture standards, unifying the representations of various gestures while extending the dataset. We then capture the correlation between speech and gestures based on a diffusion model architecture using cross-local attention and self-attention to generate better speech-matched and realistic gestures. To further align speech and gesture and increase diversity, we incorporate reinforcement learning on the discrete gesture units with a learned reward function. Extensive experiments show that UnifiedGesture outperforms recent approaches on speech-driven gesture generation in terms of CCA, FGD, and human-likeness. All code, pre-trained models, databases, and demos are available to the public at https://github.com/YoungSeng/UnifiedGesture.

Tianyi Lu, Xing Zhang, Jiaxi Gu et al.

Latent Diffusion Models (LDMs) are renowned for their powerful capabilities in image and video synthesis. Yet, compared to text-to-image (T2I) editing, text-to-video (T2V) editing suffers from a lack of decent temporal consistency and structure, due to insufficient pre-training data, limited model editability, or extensive tuning costs. To address this gap, we propose FLDM (Fused Latent Diffusion Model), a training-free framework that achieves high-quality T2V editing by integrating various T2I and T2V LDMs. Specifically, FLDM utilizes a hyper-parameter with an update schedule to effectively fuse image and video latents during the denoising process. This paper is the first to reveal that T2I and T2V LDMs can complement each other in terms of structure and temporal consistency, ultimately generating high-quality videos. It is worth noting that FLDM can serve as a versatile plugin, applicable to off-the-shelf image and video LDMs, to significantly enhance the quality of video editing. Extensive quantitative and qualitative experiments on popular T2I and T2V LDMs demonstrate FLDM's superior editing quality than state-of-the-art T2V editing methods. Our project code is available at https://github.com/lutianyi0603/fuse_your_latents.

Cuican Yu, Guansong Lu, Yihan Zeng et al. · tsinghua

Generating 3D faces from textual descriptions has a multitude of applications, such as gaming, movie, and robotics. Recent progresses have demonstrated the success of unconditional 3D face generation and text-to-3D shape generation. However, due to the limited text-3D face data pairs, text-driven 3D face generation remains an open problem. In this paper, we propose a text-guided 3D faces generation method, refer as TG-3DFace, for generating realistic 3D faces using text guidance. Specifically, we adopt an unconditional 3D face generation framework and equip it with text conditions, which learns the text-guided 3D face generation with only text-2D face data. On top of that, we propose two text-to-face cross-modal alignment techniques, including the global contrastive learning and the fine-grained alignment module, to facilitate high semantic consistency between generated 3D faces and input texts. Besides, we present directional classifier guidance during the inference process, which encourages creativity for out-of-domain generations. Compared to the existing methods, TG-3DFace creates more realistic and aesthetically pleasing 3D faces, boosting 9% multi-view consistency (MVIC) over Latent3D. The rendered face images generated by TG-3DFace achieve higher FID and CLIP score than text-to-2D face/image generation models, demonstrating our superiority in generating realistic and semantic-consistent textures.

Yinglong Wang, Zhen Liu, Jianzhuang Liu et al.

This paper presents a novel network structure with illumination-aware gamma correction and complete image modelling to solve the low-light image enhancement problem. Low-light environments usually lead to less informative large-scale dark areas, directly learning deep representations from low-light images is insensitive to recovering normal illumination. We propose to integrate the effectiveness of gamma correction with the strong modelling capacities of deep networks, which enables the correction factor gamma to be learned in a coarse to elaborate manner via adaptively perceiving the deviated illumination. Because exponential operation introduces high computational complexity, we propose to use Taylor Series to approximate gamma correction, accelerating the training and inference speed. Dark areas usually occupy large scales in low-light images, common local modelling structures, e.g., CNN, SwinIR, are thus insufficient to recover accurate illumination across whole low-light images. We propose a novel Transformer block to completely simulate the dependencies of all pixels across images via a local-to-global hierarchical attention mechanism, so that dark areas could be inferred by borrowing the information from far informative regions in a highly effective manner. Extensive experiments on several benchmark datasets demonstrate that our approach outperforms state-of-the-art methods.

Sicheng Yang, Haiwei Xue, Zhensong Zhang et al.

In this paper, we introduce the DiffuseStyleGesture+, our solution for the Generation and Evaluation of Non-verbal Behavior for Embodied Agents (GENEA) Challenge 2023, which aims to foster the development of realistic, automated systems for generating conversational gestures. Participants are provided with a pre-processed dataset and their systems are evaluated through crowdsourced scoring. Our proposed model, DiffuseStyleGesture+, leverages a diffusion model to generate gestures automatically. It incorporates a variety of modalities, including audio, text, speaker ID, and seed gestures. These diverse modalities are mapped to a hidden space and processed by a modified diffusion model to produce the corresponding gesture for a given speech input. Upon evaluation, the DiffuseStyleGesture+ demonstrated performance on par with the top-tier models in the challenge, showing no significant differences with those models in human-likeness, appropriateness for the interlocutor, and achieving competitive performance with the best model on appropriateness for agent speech. This indicates that our model is competitive and effective in generating realistic and appropriate gestures for given speech. The code, pre-trained models, and demos are available at https://github.com/YoungSeng/DiffuseStyleGesture/tree/DiffuseStyleGesturePlus/BEAT-TWH-main.

Jiaxi Gu, Shicong Wang, Haoyu Zhao et al.

Inspired by the remarkable success of Latent Diffusion Models (LDMs) for image synthesis, we study LDM for text-to-video generation, which is a formidable challenge due to the computational and memory constraints during both model training and inference. A single LDM is usually only capable of generating a very limited number of video frames. Some existing works focus on separate prediction models for generating more video frames, which suffer from additional training cost and frame-level jittering, however. In this paper, we propose a framework called "Reuse and Diffuse" dubbed $\textit{VidRD}$ to produce more frames following the frames already generated by an LDM. Conditioned on an initial video clip with a small number of frames, additional frames are iteratively generated by reusing the original latent features and following the previous diffusion process. Besides, for the autoencoder used for translation between pixel space and latent space, we inject temporal layers into its decoder and fine-tune these layers for higher temporal consistency. We also propose a set of strategies for composing video-text data that involve diverse content from multiple existing datasets including video datasets for action recognition and image-text datasets. Extensive experiments show that our method achieves good results in both quantitative and qualitative evaluations. Our project page is available $\href{https://anonymous0x233.github.io/ReuseAndDiffuse/}{here}$.

Tianyu Huang, Yihan Zeng, Bowen Dong et al.

Recent works learn 3D representation explicitly under text-3D guidance. However, limited text-3D data restricts the vocabulary scale and text control of generations. Generators may easily fall into a stereotype concept for certain text prompts, thus losing open-vocabulary generation ability. To tackle this issue, we introduce a conditional 3D generative model, namely TextField3D. Specifically, rather than using the text prompts as input directly, we suggest to inject dynamic noise into the latent space of given text prompts, i.e., Noisy Text Fields (NTFs). In this way, limited 3D data can be mapped to the appropriate range of textual latent space that is expanded by NTFs. To this end, an NTFGen module is proposed to model general text latent code in noisy fields. Meanwhile, an NTFBind module is proposed to align view-invariant image latent code to noisy fields, further supporting image-conditional 3D generation. To guide the conditional generation in both geometry and texture, multi-modal discrimination is constructed with a text-3D discriminator and a text-2.5D discriminator. Compared to previous methods, TextField3D includes three merits: 1) large vocabulary, 2) text consistency, and 3) low latency. Extensive experiments demonstrate that our method achieves a potential open-vocabulary 3D generation capability.

Qingping Zheng, Yuanfan Guo, Jiankang Deng et al.

Stable diffusion, a generative model used in text-to-image synthesis, frequently encounters resolution-induced composition problems when generating images of varying sizes. This issue primarily stems from the model being trained on pairs of single-scale images and their corresponding text descriptions. Moreover, direct training on images of unlimited sizes is unfeasible, as it would require an immense number of text-image pairs and entail substantial computational expenses. To overcome these challenges, we propose a two-stage pipeline named Any-Size-Diffusion (ASD), designed to efficiently generate well-composed images of any size, while minimizing the need for high-memory GPU resources. Specifically, the initial stage, dubbed Any Ratio Adaptability Diffusion (ARAD), leverages a selected set of images with a restricted range of ratios to optimize the text-conditional diffusion model, thereby improving its ability to adjust composition to accommodate diverse image sizes. To support the creation of images at any desired size, we further introduce a technique called Fast Seamless Tiled Diffusion (FSTD) at the subsequent stage. This method allows for the rapid enlargement of the ASD output to any high-resolution size, avoiding seaming artifacts or memory overloads. Experimental results on the LAION-COCO and MM-CelebA-HQ benchmarks demonstrate that ASD can produce well-structured images of arbitrary sizes, cutting down the inference time by 2x compared to the traditional tiled algorithm.

Roy Miles, Aysim Toker, Andreea-Maria Oncescu et al.

Reasoning with large language models often benefits from generating multiple chains-of-thought, but existing aggregation strategies are typically trajectory-level (e.g., selecting the best trace or voting on the final answer), discarding useful intermediate work from partial or "nearly correct" attempts. We propose Stitching Noisy Diffusion Thoughts, a self-consistency framework that turns cheap diffusion-sampled reasoning into a reusable pool of step-level candidates. Given a problem, we (i) sample many diverse, low-cost reasoning trajectories using a masked diffusion language model, (ii) score every intermediate step with an off-the-shelf process reward model (PRM), and (iii) stitch these highest-quality steps across trajectories into a composite rationale. This rationale then conditions an autoregressive (AR) model (solver) to recompute only the final answer. This modular pipeline separates exploration (diffusion) from evaluation and solution synthesis, avoiding monolithic unified hybrids while preserving broad search. Across math reasoning benchmarks, we find that step-level recombination is most beneficial on harder problems, and ablations highlight the importance of the final AR solver in converting stitched but imperfect rationales into accurate answers. Using low-confidence diffusion sampling with parallel, independent rollouts, our training-free framework improves average accuracy by up to 23.8% across six math and coding tasks. At the same time, it achieves up to a 1.8x latency reduction relative to both traditional diffusion models (e.g., Dream, LLaDA) and unified architectures (e.g., TiDAR). Code is available at https://github.com/roymiles/diffusion-stitching.

Dong Huo, Zixin Guo, Xinxin Zuo et al.

Given a 3D mesh, we aim to synthesize 3D textures that correspond to arbitrary textual descriptions. Current methods for generating and assembling textures from sampled views often result in prominent seams or excessive smoothing. To tackle these issues, we present TexGen, a novel multi-view sampling and resampling framework for texture generation leveraging a pre-trained text-to-image diffusion model. For view consistent sampling, first of all we maintain a texture map in RGB space that is parameterized by the denoising step and updated after each sampling step of the diffusion model to progressively reduce the view discrepancy. An attention-guided multi-view sampling strategy is exploited to broadcast the appearance information across views. To preserve texture details, we develop a noise resampling technique that aids in the estimation of noise, generating inputs for subsequent denoising steps, as directed by the text prompt and current texture map. Through an extensive amount of qualitative and quantitative evaluations, we demonstrate that our proposed method produces significantly better texture quality for diverse 3D objects with a high degree of view consistency and rich appearance details, outperforming current state-of-the-art methods. Furthermore, our proposed texture generation technique can also be applied to texture editing while preserving the original identity. More experimental results are available at https://dong-huo.github.io/TexGen/

Yuxuan Mu, Xinxin Zuo, Chuan Guo et al.

We present GSD, a diffusion model approach based on Gaussian Splatting (GS) representation for 3D object reconstruction from a single view. Prior works suffer from inconsistent 3D geometry or mediocre rendering quality due to improper representations. We take a step towards resolving these shortcomings by utilizing the recent state-of-the-art 3D explicit representation, Gaussian Splatting, and an unconditional diffusion model. This model learns to generate 3D objects represented by sets of GS ellipsoids. With these strong generative 3D priors, though learning unconditionally, the diffusion model is ready for view-guided reconstruction without further model fine-tuning. This is achieved by propagating fine-grained 2D features through the efficient yet flexible splatting function and the guided denoising sampling process. In addition, a 2D diffusion model is further employed to enhance rendering fidelity, and improve reconstructed GS quality by polishing and re-using the rendered images. The final reconstructed objects explicitly come with high-quality 3D structure and texture, and can be efficiently rendered in arbitrary views. Experiments on the challenging real-world CO3D dataset demonstrate the superiority of our approach. Project page: https://yxmu.foo/GSD/

Yunhe Wang, Kai Han, Huiling Zhen et al.

The paradigm of Large Language Models (LLMs) is currently defined by auto-regressive (AR) architectures, which generate text through a sequential ``brick-by-brick'' process. Despite their success, AR models are inherently constrained by a causal bottleneck that limits global structural foresight and iterative refinement. Diffusion Language Models (DLMs) offer a transformative alternative, conceptualizing text generation as a holistic, bidirectional denoising process akin to a sculptor refining a masterpiece. However, the potential of DLMs remains largely untapped as they are frequently confined within AR-legacy infrastructures and optimization frameworks. In this Perspective, we identify ten fundamental challenges ranging from architectural inertia and gradient sparsity to the limitations of linear reasoning that prevent DLMs from reaching their ``GPT-4 moment''. We propose a strategic roadmap organized into four pillars: foundational infrastructure, algorithmic optimization, cognitive reasoning, and unified multimodal intelligence. By shifting toward a diffusion-native ecosystem characterized by multi-scale tokenization, active remasking, and latent thinking, we can move beyond the constraints of the causal horizon. We argue that this transition is essential for developing next-generation AI capable of complex structural reasoning, dynamic self-correction, and seamless multimodal integration.

Chenhan Jiang, Yu Chen, Qingwen Zhang et al.

The development of generalizable Novel View Synthesis (NVS) models is critically limited by the scarcity of large-scale training data featuring diverse and precise camera trajectories. While real-world captures are photorealistic, they are typically sparse and discrete. Conversely, synthetic data scales but suffers from a domain gap and often lacks realistic semantics. We introduce FreeScale, a novel framework that leverages the power of scene reconstruction to transform limited real-world image sequences into a scalable source of high-quality training data. Our key insight is that an imperfect reconstructed scene serves as a rich geometric proxy, but naively sampling from it amplifies artifacts. To this end, we propose a certainty-aware free-view sampling strategy identifying novel viewpoints that are both semantically meaningful and minimally affected by reconstruction errors. We demonstrate FreeScale's effectiveness by scaling up the training of feedforward NVS models, achieving a notable gain of 2.7 dB in PSNR on challenging out-of-distribution benchmarks. Furthermore, we show that the generated data can actively enhance per-scene 3D Gaussian Splatting optimization, leading to consistent improvements across multiple datasets. Our work provides a practical and powerful data generation engine to overcome a fundamental bottleneck in 3D vision. Project page: https://mvp-ai-lab.github.io/FreeScale.

Bin Ren, Yawei Li, Nancy Mehta et al.

This paper provides a comprehensive review of the NTIRE 2024 challenge, focusing on efficient single-image super-resolution (ESR) solutions and their outcomes. The task of this challenge is to super-resolve an input image with a magnification factor of x4 based on pairs of low and corresponding high-resolution images. The primary objective is to develop networks that optimize various aspects such as runtime, parameters, and FLOPs, while still maintaining a peak signal-to-noise ratio (PSNR) of approximately 26.90 dB on the DIV2K_LSDIR_valid dataset and 26.99 dB on the DIV2K_LSDIR_test dataset. In addition, this challenge has 4 tracks including the main track (overall performance), sub-track 1 (runtime), sub-track 2 (FLOPs), and sub-track 3 (parameters). In the main track, all three metrics (ie runtime, FLOPs, and parameter count) were considered. The ranking of the main track is calculated based on a weighted sum-up of the scores of all other sub-tracks. In sub-track 1, the practical runtime performance of the submissions was evaluated, and the corresponding score was used to determine the ranking. In sub-track 2, the number of FLOPs was considered. The score calculated based on the corresponding FLOPs was used to determine the ranking. In sub-track 3, the number of parameters was considered. The score calculated based on the corresponding parameters was used to determine the ranking. RLFN is set as the baseline for efficiency measurement. The challenge had 262 registered participants, and 34 teams made valid submissions. They gauge the state-of-the-art in efficient single-image super-resolution. To facilitate the reproducibility of the challenge and enable other researchers to build upon these findings, the code and the pre-trained model of validated solutions are made publicly available at https://github.com/Amazingren/NTIRE2024_ESR/.

Qianyun He, Xinya Ji, Yicheng Gong et al.

We present a novel approach for synthesizing 3D talking heads with controllable emotion, featuring enhanced lip synchronization and rendering quality. Despite significant progress in the field, prior methods still suffer from multi-view consistency and a lack of emotional expressiveness. To address these issues, we collect EmoTalk3D dataset with calibrated multi-view videos, emotional annotations, and per-frame 3D geometry. By training on the EmoTalk3D dataset, we propose a \textit{`Speech-to-Geometry-to-Appearance'} mapping framework that first predicts faithful 3D geometry sequence from the audio features, then the appearance of a 3D talking head represented by 4D Gaussians is synthesized from the predicted geometry. The appearance is further disentangled into canonical and dynamic Gaussians, learned from multi-view videos, and fused to render free-view talking head animation. Moreover, our model enables controllable emotion in the generated talking heads and can be rendered in wide-range views. Our method exhibits improved rendering quality and stability in lip motion generation while capturing dynamic facial details such as wrinkles and subtle expressions. Experiments demonstrate the effectiveness of our approach in generating high-fidelity and emotion-controllable 3D talking heads. The code and EmoTalk3D dataset are released at https://nju-3dv.github.io/projects/EmoTalk3D.

Tianyu Huang, Yihan Zeng, Zhilu Zhang et al.

3D generation has raised great attention in recent years. With the success of text-to-image diffusion models, the 2D-lifting technique becomes a promising route to controllable 3D generation. However, these methods tend to present inconsistent geometry, which is also known as the Janus problem. We observe that the problem is caused mainly by two aspects, i.e., viewpoint bias in 2D diffusion models and overfitting of the optimization objective. To address it, we propose a two-stage 2D-lifting framework, namely DreamControl, which optimizes coarse NeRF scenes as 3D self-prior and then generates fine-grained objects with control-based score distillation. Specifically, adaptive viewpoint sampling and boundary integrity metric are proposed to ensure the consistency of generated priors. The priors are then regarded as input conditions to maintain reasonable geometries, in which conditional LoRA and weighted score are further proposed to optimize detailed textures. DreamControl can generate high-quality 3D content in terms of both geometry consistency and texture fidelity. Moreover, our control-based optimization guidance is applicable to more downstream tasks, including user-guided generation and 3D animation. The project page is available at https://github.com/tyhuang0428/DreamControl.

Yuxuan Huang, Yihang Chen, Haozheng Zhang et al.

The rapid progress of Large Language Models (LLMs) has given rise to a new category of autonomous AI systems, referred to as Deep Research (DR) agents. These agents are designed to tackle complex, multi-turn informational research tasks by leveraging a combination of dynamic reasoning, adaptive long-horizon planning, multi-hop information retrieval, iterative tool use, and the generation of structured analytical reports. In this paper, we conduct a detailed analysis of the foundational technologies and architectural components that constitute Deep Research agents. We begin by reviewing information acquisition strategies, contrasting API-based retrieval methods with browser-based exploration. We then examine modular tool-use frameworks, including code execution, multimodal input processing, and the integration of Model Context Protocols (MCPs) to support extensibility and ecosystem development. To systematize existing approaches, we propose a taxonomy that differentiates between static and dynamic workflows, and we classify agent architectures based on planning strategies and agent composition, including single-agent and multi-agent configurations. We also provide a critical evaluation of current benchmarks, highlighting key limitations such as restricted access to external knowledge, sequential execution inefficiencies, and misalignment between evaluation metrics and the practical objectives of DR agents. Finally, we outline open challenges and promising directions for future research. A curated and continuously updated repository of DR agent research is available at: {https://github.com/ai-agents-2030/awesome-deep-research-agent}.

Xu He, Qiaochu Huang, Zhensong Zhang et al.

Co-speech gestures, if presented in the lively form of videos, can achieve superior visual effects in human-machine interaction. While previous works mostly generate structural human skeletons, resulting in the omission of appearance information, we focus on the direct generation of audio-driven co-speech gesture videos in this work. There are two main challenges: 1) A suitable motion feature is needed to describe complex human movements with crucial appearance information. 2) Gestures and speech exhibit inherent dependencies and should be temporally aligned even of arbitrary length. To solve these problems, we present a novel motion-decoupled framework to generate co-speech gesture videos. Specifically, we first introduce a well-designed nonlinear TPS transformation to obtain latent motion features preserving essential appearance information. Then a transformer-based diffusion model is proposed to learn the temporal correlation between gestures and speech, and performs generation in the latent motion space, followed by an optimal motion selection module to produce long-term coherent and consistent gesture videos. For better visual perception, we further design a refinement network focusing on missing details of certain areas. Extensive experimental results show that our proposed framework significantly outperforms existing approaches in both motion and video-related evaluations. Our code, demos, and more resources are available at https://github.com/thuhcsi/S2G-MDDiffusion.

Qingping Zheng, Ling Zheng, Yuanfan Guo et al.

Artifact-free super-resolution (SR) aims to translate low-resolution images into their high-resolution counterparts with a strict integrity of the original content, eliminating any distortions or synthetic details. While traditional diffusion-based SR techniques have demonstrated remarkable abilities to enhance image detail, they are prone to artifact introduction during iterative procedures. Such artifacts, ranging from trivial noise to unauthentic textures, deviate from the true structure of the source image, thus challenging the integrity of the super-resolution process. In this work, we propose Self-Adaptive Reality-Guided Diffusion (SARGD), a training-free method that delves into the latent space to effectively identify and mitigate the propagation of artifacts. Our SARGD begins by using an artifact detector to identify implausible pixels, creating a binary mask that highlights artifacts. Following this, the Reality Guidance Refinement (RGR) process refines artifacts by integrating this mask with realistic latent representations, improving alignment with the original image. Nonetheless, initial realistic-latent representations from lower-quality images result in over-smoothing in the final output. To address this, we introduce a Self-Adaptive Guidance (SAG) mechanism. It dynamically computes a reality score, enhancing the sharpness of the realistic latent. These alternating mechanisms collectively achieve artifact-free super-resolution. Extensive experiments demonstrate the superiority of our method, delivering detailed artifact-free high-resolution images while reducing sampling steps by 2X. We release our code at https://github.com/ProAirVerse/Self-Adaptive-Guidance-Diffusion.git.

Weitong Cai, Hang Zhang, Yukai Huang et al.

Always-on sensing is essential for next-generation edge/wearable AI systems, yet continuous high-fidelity RGB video capture remains prohibitively expensive for resource-constrained mobile and edge platforms. We present a new paradigm for efficient streaming video understanding: grayscale-always, color-on-demand. Through preliminary studies, we discover that color is not always necessary. Sparse RGB frames suffice for comparable performance when temporal structure is preserved via continuous grayscale streams. Building on this insight, we propose ColorTrigger, an online training-free trigger that selectively activates color capture based on windowed grayscale affinity analysis. Designed for real-time edge deployment, ColorTrigger uses lightweight quadratic programming to detect chromatic redundancy causally, coupled with credit-budgeted control and dynamic token routing to jointly reduce sensing and inference costs. On streaming video understanding benchmarks, ColorTrigger achieves 91.6% of full-color baseline performance while using only 8.1% RGB frames, demonstrating substantial color redundancy in natural videos and enabling practical always-on video sensing on resource-constrained devices.

Xiangjun Gao, Zhensong Zhang, Dave Zhenyu Chen et al.

We propose Map2Thought, a framework that enables explicit and interpretable spatial reasoning for 3D VLMs. The framework is grounded in two key components: Metric Cognitive Map (Metric-CogMap) and Cognitive Chain-of-Thought (Cog-CoT). Metric-CogMap provides a unified spatial representation by integrating a discrete grid for relational reasoning with a continuous, metric-scale representation for precise geometric understanding. Building upon the Metric-CogMap, Cog-CoT performs explicit geometric reasoning through deterministic operations, including vector operations, bounding-box distances, and occlusion-aware appearance order cues, producing interpretable inference traces grounded in 3D structure. Experimental results show that Map2Thought enables explainable 3D understanding, achieving 59.9% accuracy using only half the supervision, closely matching the 60.9% baseline trained with the full dataset. It consistently outperforms state-of-the-art methods by 5.3%, 4.8%, and 4.0% under 10%, 25%, and 50% training subsets, respectively, on the VSI-Bench.

Arthur Moreau, Richard Shaw, Michal Nazarczuk et al.

Feed-forward 3D Gaussian Splatting (3DGS) models enable real-time scene generation but are hindered by suboptimal pixel-aligned primitive placement, which relies on a dense, rigid grid and limits both quality and efficiency. We introduce a new feed-forward architecture that detects 3D Gaussian primitives at a sub-pixel level, replacing the pixel grid with an adaptive, "Off The Grid" distribution. Inspired by keypoint detection, our multi-resolution decoder learns to distribute primitives across image patches. This module is trained end-to-end with a 3D reconstruction backbone using self-supervised learning. Our resulting pose-free model generates photorealistic scenes in seconds, achieving state-of-the-art novel view synthesis for feed-forward models. It outperforms competitors while using far fewer primitives, demonstrating a more accurate and efficient allocation that captures fine details and reduces artifacts. Moreover, we observe that by learning to render 3D Gaussians, our 3D reconstruction backbone improves camera pose estimation, suggesting opportunities to train these foundational models without labels.

Zheng Gao, Debin Meng, Yunqi Miao et al.

Current diffusion-based makeup transfer methods commonly use the makeup information encoded by off-the-shelf foundation models (e.g., CLIP) as condition to preserve the makeup style of reference image in the generation. Although effective, these works mainly have two limitations: (1) foundation models pre-trained for generic tasks struggle to capture makeup styles; (2) the makeup features of reference image are injected to the diffusion denoising model as a whole for global makeup transfer, overlooking the facial region-aware makeup features (i.e., eyes, mouth, etc) and limiting the regional controllability for region-specific makeup transfer. To address these, in this work, we propose Facial Region-Aware Makeup features (FRAM), which has two stages: (1) makeup CLIP fine-tuning; (2) identity and facial region-aware makeup injection. For makeup CLIP fine-tuning, unlike prior works using off-the-shelf CLIP, we synthesize annotated makeup style data using GPT-o3 and text-driven image editing model, and then use the data to train a makeup CLIP encoder through self-supervised and image-text contrastive learning. For identity and facial region-aware makeup injection, we construct before-and-after makeup image pairs from the edited images in stage 1 and then use them to learn to inject identity of source image and makeup of reference image to the diffusion denoising model for makeup transfer. Specifically, we use learnable tokens to query the makeup CLIP encoder to extract facial region-aware makeup features for makeup injection, which is learned via an attention loss to enable regional control. As for identity injection, we use a ControlNet Union to encode source image and its 3D mesh simultaneously. The experimental results verify the superiority of our regional controllability and our makeup transfer performance.

Jiaqi Lin, Zhihao Li, Xiao Tang et al. · pku

Existing NeRF-based methods for large scene reconstruction often have limitations in visual quality and rendering speed. While the recent 3D Gaussian Splatting works well on small-scale and object-centric scenes, scaling it up to large scenes poses challenges due to limited video memory, long optimization time, and noticeable appearance variations. To address these challenges, we present VastGaussian, the first method for high-quality reconstruction and real-time rendering on large scenes based on 3D Gaussian Splatting. We propose a progressive partitioning strategy to divide a large scene into multiple cells, where the training cameras and point cloud are properly distributed with an airspace-aware visibility criterion. These cells are merged into a complete scene after parallel optimization. We also introduce decoupled appearance modeling into the optimization process to reduce appearance variations in the rendered images. Our approach outperforms existing NeRF-based methods and achieves state-of-the-art results on multiple large scene datasets, enabling fast optimization and high-fidelity real-time rendering.

Runqi Wang, Xiaoyue Duan, Guoliang Kang et al.

Continual learning aims to enable a model to incrementally learn knowledge from sequentially arrived data. Previous works adopt the conventional classification architecture, which consists of a feature extractor and a classifier. The feature extractor is shared across sequentially arrived tasks or classes, but one specific group of weights of the classifier corresponding to one new class should be incrementally expanded. Consequently, the parameters of a continual learner gradually increase. Moreover, as the classifier contains all historical arrived classes, a certain size of the memory is usually required to store rehearsal data to mitigate classifier bias and catastrophic forgetting. In this paper, we propose a non-incremental learner, named AttriCLIP, to incrementally extract knowledge of new classes or tasks. Specifically, AttriCLIP is built upon the pre-trained visual-language model CLIP. Its image encoder and text encoder are fixed to extract features from both images and text. Text consists of a category name and a fixed number of learnable parameters which are selected from our designed attribute word bank and serve as attributes. As we compute the visual and textual similarity for classification, AttriCLIP is a non-incremental learner. The attribute prompts, which encode the common knowledge useful for classification, can effectively mitigate the catastrophic forgetting and avoid constructing a replay memory. We evaluate our AttriCLIP and compare it with CLIP-based and previous state-of-the-art continual learning methods in realistic settings with domain-shift and long-sequence learning. The results show that our method performs favorably against previous state-of-the-arts. The implementation code can be available at https://github.com/bhrqw/AttriCLIP.

Runqi Wang, Hao Zheng, Xiaoyue Duan et al.

Pre-trained vision-language models have inspired much research on few-shot learning. However, with only a few training images, there exist two crucial problems: (1) the visual feature distributions are easily distracted by class-irrelevant information in images, and (2) the alignment between the visual and language feature distributions is difficult. To deal with the distraction problem, we propose a Selective Attack module, which consists of trainable adapters that generate spatial attention maps of images to guide the attacks on class-irrelevant image areas. By messing up these areas, the critical features are captured and the visual distributions of image features are calibrated. To better align the visual and language feature distributions that describe the same object class, we propose a cross-modal distribution alignment module, in which we introduce a vision-language prototype for each class to align the distributions, and adopt the Earth Mover's Distance (EMD) to optimize the prototypes. For efficient computation, the upper bound of EMD is derived. In addition, we propose an augmentation strategy to increase the diversity of the images and the text prompts, which can reduce overfitting to the few-shot training images. Extensive experiments on 11 datasets demonstrate that our method consistently outperforms prior arts in few-shot learning. The implementation code will be available at https://github.com/bhrqw/SADA.

Zhihao Liang, Zhihao Li, Songcen Xu et al.

Instance segmentation in 3D scenes is fundamental in many applications of scene understanding. It is yet challenging due to the compound factors of data irregularity and uncertainty in the numbers of instances. State-of-the-art methods largely rely on a general pipeline that first learns point-wise features discriminative at semantic and instance levels, followed by a separate step of point grouping for proposing object instances. While promising, they have the shortcomings that (1) the second step is not supervised by the main objective of instance segmentation, and (2) their point-wise feature learning and grouping are less effective to deal with data irregularities, possibly resulting in fragmented segmentations. To address these issues, we propose in this work an end-to-end solution of Semantic Superpoint Tree Network (SSTNet) for proposing object instances from scene points. Key in SSTNet is an intermediate, semantic superpoint tree (SST), which is constructed based on the learned semantic features of superpoints, and which will be traversed and split at intermediate tree nodes for proposals of object instances. We also design in SSTNet a refinement module, termed CliqueNet, to prune superpoints that may be wrongly grouped into instance proposals. Experiments on the benchmarks of ScanNet and S3DIS show the efficacy of our proposed method. At the time of submission, SSTNet ranks top on the ScanNet (V2) leaderboard, with 2% higher of mAP than the second best method. The source code in PyTorch is available at https://github.com/Gorilla-Lab-SCUT/SSTNet.

Tianning Yuan, Fang Wan, Mengying Fu et al.

Despite the substantial progress of active learning for image recognition, there still lacks an instance-level active learning method specified for object detection. In this paper, we propose Multiple Instance Active Object Detection (MI-AOD), to select the most informative images for detector training by observing instance-level uncertainty. MI-AOD defines an instance uncertainty learning module, which leverages the discrepancy of two adversarial instance classifiers trained on the labeled set to predict instance uncertainty of the unlabeled set. MI-AOD treats unlabeled images as instance bags and feature anchors in images as instances, and estimates the image uncertainty by re-weighting instances in a multiple instance learning (MIL) fashion. Iterative instance uncertainty learning and re-weighting facilitate suppressing noisy instances, toward bridging the gap between instance uncertainty and image-level uncertainty. Experiments validate that MI-AOD sets a solid baseline for instance-level active learning. On commonly used object detection datasets, MI-AOD outperforms state-of-the-art methods with significant margins, particularly when the labeled sets are small. Code is available at https://github.com/yuantn/MI-AOD.

Jialun Peng, Dong Liu, Songcen Xu et al.

Given an incomplete image without additional constraint, image inpainting natively allows for multiple solutions as long as they appear plausible. Recently, multiplesolution inpainting methods have been proposed and shown the potential of generating diverse results. However, these methods have difficulty in ensuring the quality of each solution, e.g. they produce distorted structure and/or blurry texture. We propose a two-stage model for diverse inpainting, where the first stage generates multiple coarse results each of which has a different structure, and the second stage refines each coarse result separately by augmenting texture. The proposed model is inspired by the hierarchical vector quantized variational auto-encoder (VQ-VAE), whose hierarchical architecture isentangles structural and textural information. In addition, the vector quantization in VQVAE enables autoregressive modeling of the discrete distribution over the structural information. Sampling from the distribution can easily generate diverse and high-quality structures, making up the first stage of our model. In the second stage, we propose a structural attention module inside the texture generation network, where the module utilizes the structural information to capture distant correlations. We further reuse the VQ-VAE to calculate two feature losses, which help improve structure coherence and texture realism, respectively. Experimental results on CelebA-HQ, Places2, and ImageNet datasets show that our method not only enhances the diversity of the inpainting solutions but also improves the visual quality of the generated multiple images. Code and models are available at: https://github.com/USTC-JialunPeng/Diverse-Structure-Inpainting.

Jiehong Lin, Zewei Wei, Zhihao Li et al.

Category-level 6D object pose and size estimation is to predict full pose configurations of rotation, translation, and size for object instances observed in single, arbitrary views of cluttered scenes. In this paper, we propose a new method of Dual Pose Network with refined learning of pose consistency for this task, shortened as DualPoseNet. DualPoseNet stacks two parallel pose decoders on top of a shared pose encoder, where the implicit decoder predicts object poses with a working mechanism different from that of the explicit one; they thus impose complementary supervision on the training of pose encoder. We construct the encoder based on spherical convolutions, and design a module of Spherical Fusion wherein for a better embedding of pose-sensitive features from the appearance and shape observations. Given no testing CAD models, it is the novel introduction of the implicit decoder that enables the refined pose prediction during testing, by enforcing the predicted pose consistency between the two decoders using a self-adaptive loss term. Thorough experiments on benchmarks of both category- and instance-level object pose datasets confirm efficacy of our designs. DualPoseNet outperforms existing methods with a large margin in the regime of high precision. Our code is released publicly at https://github.com/Gorilla-Lab-SCUT/DualPoseNet.

Lu Yang, Qing Song, Zhihui Wang et al.

How to estimate the quality of the network output is an important issue, and currently there is no effective solution in the field of human parsing. In order to solve this problem, this work proposes a statistical method based on the output probability map to calculate the pixel quality information, which is called pixel score. In addition, the Quality-Aware Module (QAM) is proposed to fuse the different quality information, the purpose of which is to estimate the quality of human parsing results. We combine QAM with a concise and effective network design to propose Quality-Aware Network (QANet) for human parsing. Benefiting from the superiority of QAM and QANet, we achieve the best performance on three multiple and one single human parsing benchmarks, including CIHP, MHP-v2, Pascal-Person-Part and LIP. Without increasing the training and inference time, QAM improves the AP$^\text{r}$ criterion by more than 10 points in the multiple human parsing task. QAM can be extended to other tasks with good quality estimation, e.g. instance segmentation. Specifically, QAM improves Mask R-CNN by ~1% mAP on COCO and LVISv1.0 datasets. Based on the proposed QAM and QANet, our overall system wins 1st place in CVPR2019 COCO DensePose Challenge, and 1st place in Track 1 & 2 of CVPR2020 LIP Challenge. Code and models are available at https://github.com/soeaver/QANet.

Lu Yang, Qing Song, Zhihui Wang et al.

Multiple human parsing aims to segment various human parts and associate each part with the corresponding instance simultaneously. This is a very challenging task due to the diverse human appearance, semantic ambiguity of different body parts, and complex background. Through analysis of multiple human parsing task, we observe that human-centric global perception and accurate instance-level parsing scoring are crucial for obtaining high-quality results. But the most state-of-the-art methods have not paid enough attention to these issues. To reverse this phenomenon, we present Renovating Parsing R-CNN (RP R-CNN), which introduces a global semantic enhanced feature pyramid network and a parsing re-scoring network into the existing high-performance pipeline. The proposed RP R-CNN adopts global semantic representation to enhance multi-scale features for generating human parsing maps, and regresses a confidence score to represent its quality. Extensive experiments show that RP R-CNN performs favorably against state-of-the-art methods on CIHP and MHP-v2 datasets. Code and models are available at https://github.com/soeaver/RP-R-CNN.

Fengyuan Shi, Jiaxi Gu, Hang Xu et al.

Diffusion models have made tremendous progress in text-driven image and video generation. Now text-to-image foundation models are widely applied to various downstream image synthesis tasks, such as controllable image generation and image editing, while downstream video synthesis tasks are less explored for several reasons. First, it requires huge memory and computation overhead to train a video generation foundation model. Even with video foundation models, additional costly training is still required for downstream video synthesis tasks. Second, although some works extend image diffusion models into videos in a training-free manner, temporal consistency cannot be well preserved. Finally, these adaption methods are specifically designed for one task and fail to generalize to different tasks. To mitigate these issues, we propose a training-free general-purpose video synthesis framework, coined as {\bf BIVDiff}, via bridging specific image diffusion models and general text-to-video foundation diffusion models. Specifically, we first use a specific image diffusion model (e.g., ControlNet and Instruct Pix2Pix) for frame-wise video generation, then perform Mixed Inversion on the generated video, and finally input the inverted latents into the video diffusion models (e.g., VidRD and ZeroScope) for temporal smoothing. This decoupled framework enables flexible image model selection for different purposes with strong task generalization and high efficiency. To validate the effectiveness and general use of BIVDiff, we perform a wide range of video synthesis tasks, including controllable video generation, video editing, video inpainting, and outpainting.

Jiayue Liu, Xiao Tang, Freeman Cheng et al. · pku

3D Gaussian Splatting showcases notable advancements in photo-realistic and real-time novel view synthesis. However, it faces challenges in modeling mirror reflections, which exhibit substantial appearance variations from different viewpoints. To tackle this problem, we present MirrorGaussian, the first method for mirror scene reconstruction with real-time rendering based on 3D Gaussian Splatting. The key insight is grounded on the mirror symmetry between the real-world space and the virtual mirror space. We introduce an intuitive dual-rendering strategy that enables differentiable rasterization of both the real-world 3D Gaussians and the mirrored counterpart obtained by reflecting the former about the mirror plane. All 3D Gaussians are jointly optimized with the mirror plane in an end-to-end framework. MirrorGaussian achieves high-quality and real-time rendering in scenes with mirrors, empowering scene editing like adding new mirrors and objects. Comprehensive experiments on multiple datasets demonstrate that our approach significantly outperforms existing methods, achieving state-of-the-art results. Project page: https://mirror-gaussian.github.io/.

Cong Wang, Jiaxi Gu, Panwen Hu et al.

Image-to-video generation, which aims to generate a video starting from a given reference image, has drawn great attention. Existing methods try to extend pre-trained text-guided image diffusion models to image-guided video generation models. Nevertheless, these methods often result in either low fidelity or flickering over time due to their limitation to shallow image guidance and poor temporal consistency. To tackle these problems, we propose a high-fidelity image-to-video generation method by devising a frame retention branch based on a pre-trained video diffusion model, named DreamVideo. Instead of integrating the reference image into the diffusion process at a semantic level, our DreamVideo perceives the reference image via convolution layers and concatenates the features with the noisy latents as model input. By this means, the details of the reference image can be preserved to the greatest extent. In addition, by incorporating double-condition classifier-free guidance, a single image can be directed to videos of different actions by providing varying prompt texts. This has significant implications for controllable video generation and holds broad application prospects. We conduct comprehensive experiments on the public dataset, and both quantitative and qualitative results indicate that our method outperforms the state-of-the-art method. Especially for fidelity, our model has a powerful image retention ability and delivers the best results in UCF101 compared to other image-to-video models to our best knowledge. Also, precise control can be achieved by giving different text prompts. Further details and comprehensive results of our model will be presented in https://anonymous0769.github.io/DreamVideo/.

Fan Li, Zixiao Zhang, Yi Huang et al.

The traditional image inpainting task aims to restore corrupted regions by referencing surrounding background and foreground. However, the object erasure task, which is in increasing demand, aims to erase objects and generate harmonious background. Previous GAN-based inpainting methods struggle with intricate texture generation. Emerging diffusion model-based algorithms, such as Stable Diffusion Inpainting, exhibit the capability to generate novel content, but they often produce incongruent results at the locations of the erased objects and require high-quality text prompt inputs. To address these challenges, we introduce MagicEraser, a diffusion model-based framework tailored for the object erasure task. It consists of two phases: content initialization and controllable generation. In the latter phase, we develop two plug-and-play modules called prompt tuning and semantics-aware attention refocus. Additionally, we propose a data construction strategy that generates training data specially suitable for this task. MagicEraser achieves fine and effective control of content generation while mitigating undesired artifacts. Experimental results highlight a valuable advancement of our approach in the object erasure task.

Xiang An, Yin Xie, Kaicheng Yang et al.

We present LLaVA-OneVision-1.5, a novel family of Large Multimodal Models (LMMs) that achieve state-of-the-art performance with significantly reduced computational and financial costs. Different from the existing works, LLaVA-OneVision-1.5 provides an open, efficient, and reproducible framework for building high-quality vision-language models entirely from scratch. The LLaVA-OneVision-1.5 release comprises three primary components: (1) Large-Scale Curated Datasets: We construct an 85M concept-balanced pretraining dataset LLaVA-OneVision-1.5-Mid-Traning and a meticulously curated 22M instruction dataset LLaVA-OneVision-1.5-Instruct. (2) Efficient Training Framework: We develop a complete end-to-end efficient training framework leveraging an offline parallel data packing strategy to facilitate the training of LLaVA-OneVision-1.5 within a $16,000 budget. (3) State-of-the-art Performance: Experimental results demonstrate that LLaVA-OneVision-1.5 yields exceptionally competitive performance across a broad range of downstream tasks. Specifically, LLaVA-OneVision-1.5-8B outperforms Qwen2.5-VL-7B on 18 of 27 benchmarks, and LLaVA-OneVision-1.5-4B surpasses Qwen2.5-VL-3B on all 27 benchmarks. We anticipate releasing LLaVA-OneVision-1.5-RL shortly and encourage the community to await further updates.

Runhui Huang, Kaixin Cai, Jianhua Han et al.

Despite the success of generating high-quality images given any text prompts by diffusion-based generative models, prior works directly generate the entire images, but cannot provide object-wise manipulation capability. To support wider real applications like professional graphic design and digital artistry, images are frequently created and manipulated in multiple layers to offer greater flexibility and control. Therefore in this paper, we propose a layer-collaborative diffusion model, named LayerDiff, specifically designed for text-guided, multi-layered, composable image synthesis. The composable image consists of a background layer, a set of foreground layers, and associated mask layers for each foreground element. To enable this, LayerDiff introduces a layer-based generation paradigm incorporating multiple layer-collaborative attention modules to capture inter-layer patterns. Specifically, an inter-layer attention module is designed to encourage information exchange and learning between layers, while a text-guided intra-layer attention module incorporates layer-specific prompts to direct the specific-content generation for each layer. A layer-specific prompt-enhanced module better captures detailed textual cues from the global prompt. Additionally, a self-mask guidance sampling strategy further unleashes the model's ability to generate multi-layered images. We also present a pipeline that integrates existing perceptual and generative models to produce a large dataset of high-quality, text-prompted, multi-layered images. Extensive experiments demonstrate that our LayerDiff model can generate high-quality multi-layered images with performance comparable to conventional whole-image generation methods. Moreover, LayerDiff enables a broader range of controllable generative applications, including layer-specific image editing and style transfer.

Haodong Zhang, ZhiKe Chen, Haocheng Xu et al.

Capturing and preserving motion semantics is essential to motion retargeting between animation characters. However, most of the previous works neglect the semantic information or rely on human-designed joint-level representations. Here, we present a novel Semantics-aware Motion reTargeting (SMT) method with the advantage of vision-language models to extract and maintain meaningful motion semantics. We utilize a differentiable module to render 3D motions. Then the high-level motion semantics are incorporated into the motion retargeting process by feeding the vision-language model with the rendered images and aligning the extracted semantic embeddings. To ensure the preservation of fine-grained motion details and high-level semantics, we adopt a two-stage pipeline consisting of skeleton-aware pre-training and fine-tuning with semantics and geometry constraints. Experimental results show the effectiveness of the proposed method in producing high-quality motion retargeting results while accurately preserving motion semantics.

Guansong Lu, Yuanfan Guo, Jianhua Han et al.

Current large-scale diffusion models represent a giant leap forward in conditional image synthesis, capable of interpreting diverse cues like text, human poses, and edges. However, their reliance on substantial computational resources and extensive data collection remains a bottleneck. On the other hand, the integration of existing diffusion models, each specialized for different controls and operating in unique latent spaces, poses a challenge due to incompatible image resolutions and latent space embedding structures, hindering their joint use. Addressing these constraints, we present "PanGu-Draw", a novel latent diffusion model designed for resource-efficient text-to-image synthesis that adeptly accommodates multiple control signals. We first propose a resource-efficient Time-Decoupling Training Strategy, which splits the monolithic text-to-image model into structure and texture generators. Each generator is trained using a regimen that maximizes data utilization and computational efficiency, cutting data preparation by 48% and reducing training resources by 51%. Secondly, we introduce "Coop-Diffusion", an algorithm that enables the cooperative use of various pre-trained diffusion models with different latent spaces and predefined resolutions within a unified denoising process. This allows for multi-control image synthesis at arbitrary resolutions without the necessity for additional data or retraining. Empirical validations of Pangu-Draw show its exceptional prowess in text-to-image and multi-control image generation, suggesting a promising direction for future model training efficiencies and generation versatility. The largest 5B T2I PanGu-Draw model is released on the Ascend platform. Project page: $\href{https://pangu-draw.github.io}{this~https~URL}$

Kai Chen, Ruiyuan Gao, Lanqing Hong et al.

In this paper, we present details of the 1st W-CODA workshop, held in conjunction with the ECCV 2024. W-CODA aims to explore next-generation solutions for autonomous driving corner cases, empowered by state-of-the-art multimodal perception and comprehension techniques. 5 Speakers from both academia and industry are invited to share their latest progress and opinions. We collect research papers and hold a dual-track challenge, including both corner case scene understanding and generation. As the pioneering effort, we will continuously bridge the gap between frontier autonomous driving techniques and fully intelligent, reliable self-driving agents robust towards corner cases.

Xing Zhang, Jiaxi Gu, Haoyu Zhao et al.

Temporal Video Grounding (TVG) aims to localize a moment from an untrimmed video given the language description. Since the annotation of TVG is labor-intensive, TVG under limited supervision has accepted attention in recent years. The great success of vision-language pre-training guides TVG to follow the traditional "pre-training + fine-tuning" paradigm, however, the pre-training process would suffer from a lack of temporal modeling and fine-grained alignment due to the difference of data nature between pre-train and test. Besides, the large gap between pretext and downstream tasks makes zero-shot testing impossible for the pre-trained model. To avoid the drawbacks of the traditional paradigm, we propose AutoTVG, a new vision-language pre-training paradigm for TVG that enables the model to learn semantic alignment and boundary regression from automatically annotated untrimmed videos. To be specific, AutoTVG consists of a novel Captioned Moment Generation (CMG) module to generate captioned moments from untrimmed videos, and TVGNet with a regression head to predict localization results. Experimental results on Charades-STA and ActivityNet Captions show that, regarding zero-shot temporal video grounding, AutoTVG achieves highly competitive performance with in-distribution methods under out-of-distribution testing, and is superior to existing pre-training frameworks with much less training data.

Xin Qin, Hanbin Zhao, Guangchen Lin et al.

Temporal action localization is an important and challenging task that aims to locate temporal regions in real-world untrimmed videos where actions occur and recognize their classes. It is widely acknowledged that video context is a critical cue for video understanding, and exploiting the context has become an important strategy to boost localization performance. However, previous state-of-the-art methods focus more on exploring semantic context which captures the feature similarity among frames or proposals, and neglect positional context which is vital for temporal localization. In this paper, we propose a temporal-position-sensitive context modeling approach to incorporate both positional and semantic information for more precise action localization. Specifically, we first augment feature representations with directed temporal positional encoding, and then conduct attention-based information propagation, in both frame-level and proposal-level. Consequently, the generated feature representations are significantly empowered with the discriminative capability of encoding the position-aware context information, and thus benefit boundary detection and proposal evaluation. We achieve state-of-the-art performance on both two challenging datasets, THUMOS-14 and ActivityNet-1.3, demonstrating the effectiveness and generalization ability of our method.

Wei Yin, Xinlong Wang, Chunhua Shen et al.

We present a method for depth estimation with monocular images, which can predict high-quality depth on diverse scenes up to an affine transformation, thus preserving accurate shapes of a scene. Previous methods that predict metric depth often work well only for a specific scene. In contrast, learning relative depth (information of being closer or further) can enjoy better generalization, with the price of failing to recover the accurate geometric shape of the scene. In this work, we propose a dataset and methods to tackle this dilemma, aiming to predict accurate depth up to an affine transformation with good generalization to diverse scenes. First we construct a large-scale and diverse dataset, termed Diverse Scene Depth dataset (DiverseDepth), which has a broad range of scenes and foreground contents. Compared with previous learning objectives, i.e., learning metric depth or relative depth, we propose to learn the affine-invariant depth using our diverse dataset to ensure both generalization and high-quality geometric shapes of scenes. Furthermore, in order to train the model on the complex dataset effectively, we propose a multi-curriculum learning method. Experiments show that our method outperforms previous methods on 8 datasets by a large margin with the zero-shot test setting, demonstrating the excellent generalization capacity of the learned model to diverse scenes. The reconstructed point clouds with the predicted depth show that our method can recover high-quality 3D shapes. Code and dataset are available at: https://tinyurl.com/DiverseDepth

Hao Lu, Yutong Dai, Chunhua Shen et al.

We show that existing upsampling operators can be unified using the notion of the index function. This notion is inspired by an observation in the decoding process of deep image matting where indices-guided unpooling can often recover boundary details considerably better than other upsampling operators such as bilinear interpolation. By viewing the indices as a function of the feature map, we introduce the concept of "learning to index", and present a novel index-guided encoder-decoder framework where indices are self-learned adaptively from data and are used to guide the downsampling and upsampling stages, without extra training supervision. At the core of this framework is a new learnable module, termed Index Network (IndexNet), which dynamically generates indices conditioned on the feature map itself. IndexNet can be used as a plug-in applying to almost all off-the-shelf convolutional networks that have coupled downsampling and upsampling stages, giving the networks the ability to dynamically capture variations of local patterns. In particular, we instantiate and investigate five families of IndexNet and demonstrate their effectiveness on four dense prediction tasks, including image denoising, image matting, semantic segmentation, and monocular depth estimation. Code and models have been made available at: https://tinyurl.com/IndexNetV1

Hao Lu, Yutong Dai, Chunhua Shen et al.

We show that existing upsampling operators can be unified with the notion of the index function. This notion is inspired by an observation in the decoding process of deep image matting where indices-guided unpooling can recover boundary details much better than other upsampling operators such as bilinear interpolation. By looking at the indices as a function of the feature map, we introduce the concept of learning to index, and present a novel index-guided encoder-decoder framework where indices are self-learned adaptively from data and are used to guide the pooling and upsampling operators, without the need of supervision. At the core of this framework is a flexible network module, termed IndexNet, which dynamically predicts indices given an input. Due to its flexibility, IndexNet can be used as a plug-in applying to any off-the-shelf convolutional networks that have coupled downsampling and upsampling stages. We demonstrate the effectiveness of IndexNet on the task of natural image matting where the quality of learned indices can be visually observed from predicted alpha mattes. Results on the Composition-1k matting dataset show that our model built on MobileNetv2 exhibits at least $16.1\%$ improvement over the seminal VGG-16 based deep matting baseline, with less training data and lower model capacity. Code and models has been made available at: https://tinyurl.com/IndexNetV1