Immersive creation tools enhance spatial understanding, yet they push animators to abandon mature 2D desktop practices; Pure desktop setups, however, lack embodied spatial manipulation, making tool switching cognitively costly. To address this issue, We present AniXDim, a cross-dimensional interaction system for 3D character animation that unifies precise planar editing and embodied spatial control without explicit mode toggles. A commodity mouse is augmented for on-demand 6DoF manipulation, and a VR controller is endowed with high-precision planar input through adaptive projection, forming bidirectional dimensional augmentation. Users simply raise or rest the device to enable near-frictionless transitions, while a single autostereoscopic desktop display adapts depth to the inferred interaction state, supporting keyframe, pose, and reference authoring within one consistent workspace. A controlled user study comparing AniXDim with pure desktop and pure VR baselines indicates significant performance gains over the desktop baseline and comparable efficiency to the VR baseline, and higher usability ratings while maintaining comparable workload. These findings suggest that near-frictionless dimensional switching can reconcile 2D precision and 3D embodiment, offering a low-learning-overhead pathway for future hybrid desktop animation pipelines and broader 2D–3D authoring domains.

Recent advances in zero-shot text-to-3D generation have revolutionised 3D content creation by enabling direct synthesis from textual descriptions. While state-of-the-art methods leverage 3D Gaussian Splatting with score distillation to enhance multi-view rendering through pre-trained text-to-image (T2I) models, they suffer from inherent prior view biases in T2I Models. These biases lead to inconsistent 3D generation, particularly manifesting as the multi-face Janus problem, where objects exhibit conflicting features across views. To address this fundamental challenge, we propose ConsDreamer, a novel method that mitigates view bias by refining both the conditional and unconditional terms in the score distillation process: (1) a View Disentanglement Module (VDM) that eliminates viewpoint biases in conditional prompts by decoupling irrelevant view components and injecting precise view control; and (2) a similarity-based partial order loss that enforces geometric consistency in the unconditional term by aligning cosine similarities with azimuth relationships. Extensive experiments demonstrate that ConsDreamer can be seamlessly integrated into various 3D representations and score distillation paradigms, effectively mitigating the multi-face Janus problem.

Online handwriting recognition based on sensor trajectory information faces several unresolved challenges: 1) sensor signals lack sufficient global spatial context; 2) different recognition tasks have inconsistent requirements for feature receptive fields. This is due to the inconsistent scales of the input sequences and the different semantic complexity of different language units. In this paper, we propose an online handwritten text recognition method based on multi-scale bimodal feature fusion to address these challenges. First, we employ sequence-generated pseudo-images to supplement the two-dimensional spatial information, and then extract multi-scale features from both trajectories and images simultaneously. Subsequently, our designed bimodal embedding learning module jointly learns feature embeddings for trajectories and images at different scales. These embeddings are then fed into a novel position-aware multi-scale fusion module to extract features for text prediction. The proposed modules effectively mitigate the issues of scales and semantics misalignment. Experimental results demonstrate significant performance improvements on various handwriting recognition datasets using our approach.