arXiv subjects

Jintao Rong

Publications and source records attributed to Jintao Rong.

7 recordsLinked to original sources

arXiv2026

Exploring Spatial Intelligence from a Generative Perspective

Spatial intelligence is essential for multimodal large language models, yet current benchmarks largely assess it only from an understanding perspective. We ask whether modern generative or unified multimodal models also possess generative spatial intelligence (GSI), the ability to respect and manipulate 3D spatial constraints during image generation, and whether such capability can be measured or improved. We introduce GSI-Bench, the first benchmark designed to quantify GSI through spatially grounded image editing. It consists of two complementary components: GSI-Real, a high-quality real-world dataset built via a 3D-prior-guided generation and filtering pipeline, and GSI-Syn, a large-scale synthetic benchmark with controllable spatial operations and fully automated labeling. Together with a unified evaluation protocol, GSI-Bench enables scalable, model-agnostic assessment of spatial compliance and editing fidelity. Experiments show that fine-tuning unified multimodal models on GSI-Syn yields substantial gains on both synthetic and real tasks and, strikingly, also improves downstream spatial understanding. This provides the first clear evidence that generative training can tangibly strengthen spatial reasoning, establishing a new pathway for advancing spatial intelligence in multimodal models.

cs.CV↗

arXiv2026

RealHD: A High-Quality Dataset for Robust Detection of State-of-the-Art AI-Generated Images

The rapid advancement of generative AI has raised concerns about the authenticity of digital images, as highly realistic fake images can now be generated at low cost, potentially increasing societal risks. In response, several datasets have been established to train detection models aimed at distinguishing AI-generated images from real ones. However, existing datasets suffer from limited generalization, low image quality, overly simple prompts, and insufficient image diversity. To address these limitations, we propose a high-quality, large-scale dataset comprising over 730,000 images across multiple categories, including both real and AI-generated images. The generated images are synthesized via state-of-the-art methods, including text-to-image generation (guided by over 10,000 carefully designed prompts), image inpainting, image refinement, and face swapping. Each generated image is annotated with its generation method and category. Inpainting images further include binary masks to indicate inpainted regions, providing rich metadata for analysis. Compared to existing datasets, detection models trained on our dataset demonstrate superior generalization capabilities. Our dataset not only serves as a strong benchmark for evaluating detection methods but also contributes to advancing the robustness of AI-generated image detection techniques. Building upon this, we propose a lightweight detection method based on image noise entropy, which transforms the original image into an entropy tensor of Non-Local Means (NLM) noise before classification. Extensive experiments demonstrate that models trained on our dataset achieve strong generalization, and our method delivers competitive performance, establishing a solid baseline for future research. The dataset and source code are publicly available at https://real-hd.github.io.

cs.CV↗

arXiv2025

When Distillation Breaks Motion Control: Restoring Generative Trajectories for Fast Video Generators

Training-free motion customization imposes motion patterns from reference videos onto video generators through test-time computation. Most existing methods target full diffusion models, requiring many denoising steps and high computational cost. With the rise of efficient distilled models, a natural question arises: can test-time motion customization be applied directly to distilled generators with their accelerated sampling and efficiency gains? However, our analysis reveals that existing training-free techniques fail on distilled models. Distillation fundamentally alters the denoising dynamics that prior test-time guidance relies on, and the large denoising steps of distilled generators discard the dense intermediate states that score guidance requires, rendering existing motion control strategies incompatible with fast generation. To address this limitation, we propose MotionEcho, a novel training-free test-time distillation framework that enables motion customization for distilled video generators. The key idea is to correct the student model's sampling trajectory with restricted usage of a high-quality diffusion teacher at inference time. Teacher supervises the student's denoising by re-noising the student's endpoint onto its dense trajectory to form a motion-aligned clean endpoint, then interpolating it with the student's, while an adaptive scheduling mechanism determines when and how much teacher guidance is needed. As a result, MotionEcho restores generative trajectories for distilled video generators via lightweight, adaptive test-time teacher guidance, enabling accurate motion control without compromising generation efficiency. Extensive experiments on multiple distilled video generation models demonstrate that our method significantly improves motion fidelity and visual quality while retaining the efficiency advantages of distilled generation.

cs.CV↗

arXiv2025

GSORB-SLAM: Gaussian Splatting SLAM benefits from ORB features and Transmittance information

The emergence of 3D Gaussian Splatting (3DGS) has recently ignited a renewed wave of research in dense visual SLAM. However, existing approaches encounter challenges, including sensitivity to artifacts and noise, suboptimal selection of training viewpoints, and the absence of global optimization. In this paper, we propose GSORB-SLAM, a dense SLAM framework that integrates 3DGS with ORB features through a tightly coupled optimization pipeline. To mitigate the effects of noise and artifacts, we propose a novel geometric representation and optimization method for tracking, which significantly enhances localization accuracy and robustness. For high-fidelity mapping, we develop an adaptive Gaussian expansion and regularization method that facilitates compact yet expressive scene modeling while suppressing redundant primitives. Furthermore, we design a hybrid graph-based viewpoint selection mechanism that effectively reduces overfitting and accelerates convergence. Extensive evaluations across various datasets demonstrate that our system achieves state-of-the-art performance in both tracking precision-improving RMSE by 16.2% compared to ORB-SLAM2 baselines-and reconstruction quality-improving PSNR by 3.93 dB compared to 3DGS-SLAM baselines. The project: https://aczheng-cai.github.io/gsorb-slam.github.io/

cs.RO↗

arXiv2024

Retrieval-Enhanced Visual Prompt Learning for Few-shot Classification

The Contrastive Language-Image Pretraining (CLIP) model has been widely used in various downstream vision tasks. The few-shot learning paradigm has been widely adopted to augment its capacity for these tasks. However, current paradigms may struggle with fine-grained classification, such as satellite image recognition, due to widening domain gaps. To address this limitation, we propose retrieval-enhanced visual prompt learning (RePrompt), which introduces retrieval mechanisms to cache and reuse the knowledge of downstream tasks. RePrompt constructs a retrieval database from either training examples or external data if available, and uses a retrieval mechanism to enhance multiple stages of a simple prompt learning baseline, thus narrowing the domain gap. During inference, our enhanced model can reference similar samples brought by retrieval to make more accurate predictions. A detailed analysis reveals that retrieval helps to improve the distribution of late features, thus, improving generalization for downstream tasks. Reprompt attains state-of-the-art performance on a wide range of vision datasets, including 11 image datasets, 3 video datasets, 1 multi-view dataset, and 4 domain generalization benchmarks.

cs.CV↗

arXiv2023

Improving Neural Indoor Surface Reconstruction with Mask-Guided Adaptive Consistency Constraints

3D scene reconstruction from 2D images has been a long-standing task. Instead of estimating per-frame depth maps and fusing them in 3D, recent research leverages the neural implicit surface as a unified representation for 3D reconstruction. Equipped with data-driven pre-trained geometric cues, these methods have demonstrated promising performance. However, inaccurate prior estimation, which is usually inevitable, can lead to suboptimal reconstruction quality, particularly in some geometrically complex regions. In this paper, we propose a two-stage training process, decouple view-dependent and view-independent colors, and leverage two novel consistency constraints to enhance detail reconstruction performance without requiring extra priors. Additionally, we introduce an essential mask scheme to adaptively influence the selection of supervision constraints, thereby improving performance in a self-supervised paradigm. Experiments on synthetic and real-world datasets show the capability of reducing the interference from prior estimation errors and achieving high-quality scene reconstruction with rich geometric details.

cs.CV↗

arXiv2022

Efficient Re-parameterization Operations Search for Easy-to-Deploy Network Based on Directional Evolutionary Strategy

Structural re-parameterization (Rep) methods has achieved significant performance improvement on traditional convolutional network. Most current Rep methods rely on prior knowledge to select the reparameterization operations. However, the performance of architecture is limited by the type of operations and prior knowledge. To break this restriction, in this work, an improved re-parameterization search space is designed, which including more type of re-parameterization operations. Concretely, the performance of convolutional networks can be further improved by the search space. To effectively explore this search space, an automatic re-parameterization enhancement strategy is designed based on neural architecture search (NAS), which can search a excellent re-parameterization architecture. Besides, we visualize the output features of the architecture to analyze the reasons for the formation of the re-parameterization architecture. On public datasets, we achieve better results. Under the same training conditions as ResNet, we improve the accuracy of ResNet-50 by 1.82% on ImageNet-1k.

cs.AI↗