Monocular dynamic scene reconstruction is a challenging task due to the inherent limitation of observing the scene from a single viewpoint at each timestamp, particularly in the presence of object motion and illumination changes. Recent methods combine Gaussian Splatting with deformation modeling to enable fast training and rendering; however, their performance in real-world scenarios strongly depends on accurate point cloud initialization. When such initialization is unavailable and random point clouds are used instead, reconstruction quality degrades significantly. To address this limitation, we propose an optimization strategy that relaxes the requirement for accurate initialization in Gaussian-Splatting-based monocular dynamic scene reconstruction. The scene is first reconstructed under a static assumption using all monocular frames, allowing stable convergence of background regions. Based on reconstruction errors, a subset of Gaussians is then activated as dynamic to model motion and deformation. In addition, an annealing jitter regularization term is introduced to improve robustness to camera pose inaccuracies commonly observed in real-world datasets. Extensive experiments on established benchmarks demonstrate that the proposed method enables stable training from randomly initialized point clouds and achieves reconstruction performance comparable to approaches relying on accurate point cloud initialization.
To address the limitations of existing optimization-based 3D style transfer methods in terms of visual quality, 3D consistency, and real-time rendering performance, we propose a novel 3D Gaussian scene style transfer method based on 2D priors and iterative optimization. Our approach introduces a progressive training pipeline that alternates between fine-tuning the 3D Gaussian field and updating a set of supervised stylized images. By gradually injecting style information into the 3D scene through iterative refinement, the method effectively preserves the geometric structure and spatial coherence across viewpoints. Furthermore, we incorporated a pre-trained stable diffusion model as a 2D prior to guide the style adaptation of the 3D Gaussian representation. The combination of diffusion priors and differentiable 3D Gaussian rendering enables high-fidelity style transfer while maintaining real-time rendering capability. Extensive experiments demonstrate that our method significantly improves the visual quality and multi-view consistency of 3D stylized scenes, offering an effective and efficient solution for real-time 3D scene stylization.
Recent large pre-trained text-to-image models possess massive prior knowledge, which can generate high-quality images with a simple prompt. However, when we need to generate a personalized object with a specific attribution description, namely, an identity , it cannot generate images that match the desired identity. Existing personalization methods for text-to-image models have the following three problems: (1) low identity fidelity, (2) low prompt fidelity and (3) low quality. To address the above issues, we propose a dual-direction fine-tuning method that guides the large pre-trained text-to-image model to generate images corresponding to the input prompt. Specifically, we input a class label into a large pre-trained text-to-image model to generate class-generalized images and caption these images using a Bootstrapping Language–Image Pre-training (BLIP) image-captioning model, obtaining class-generalized prompts. The two fine-tuning directions are ID-strengthen and ID-weaken directions. For the ID-strengthen direction, we append up-weighted at the beginning of a class-generalized prompt to obtain an ID-strengthen prompt, then we use the reference images of and the ID-strengthen prompt to fine-tune the pre-trained model. For the ID-weaken direction, we append down-weighted , obtain an ID-weaken prompt, and fine-tune the pre-trained model. In addition, we propose an attentive attribution alignment strategy to align the semantic information of the weighted prompts to the class-generalized prompts. Qualitative and quantitative experiments show that our method improves identity fidelity and prompt fidelity while maintaining high visual quality.