KwanMyung Kim | Searcharxiv

arXiv2026

Capable but Not Scalable: Requirements and Interaction Costs of Building Multi-View CAD Datasets for Design Research

Transforming CAD models into consistent multi-view image datasets is increasingly important for AI-driven product design research, yet existing workflows can impose substantial burdens on researchers without programming expertise. We examine this challenge from a human-computer interaction (HCI) perspective by analyzing ten reported rendering practices and deriving fourteen requirements spanning dataset quality, visual consistency, and user interaction. We then assess eleven development- and design-oriented tools against an illustrative task involving STEP models, interpreting potential interaction costs through the cognitive dimensions framework. Our analysis reveals a gap between technical capability and practical scalability: programming-based frameworks offer flexible automation but require coding expertise, while graphical design tools provide accessible functionality yet retain repetitive per-product operations. No assessed workflow combines a low programming threshold, low repetition viscosity, and flexible protocol configuration. Based on these findings, we propose design directions including reusable rendering presets, collection-wide previews and corrections, mixed-initiative orientation assignment, and automatic provenance recording. This work reframes CAD dataset generation as an end-user interaction design problem and establishes requirements for more accessible, scalable dataset creation tools.

cs.HC↗

arXiv2026

Synthetic Realities: Evaluating Human Ability to Distinguish AIGenerated Videos from Real Footage

Recent advances in generative AI have enabled multiple pathways for high-fidelity video synthesis: text-to-video, image-to-video animation, and video outpainting. Empirical side-by-side evaluations of how untrained viewers perceive and distinguish these outputs from real footage remain scarce. In this study, we systematically compare human detection accuracy across these three AI generation techniques within three thematic contexts: historical footage, film and media content, and natural environments. We constructed a balanced stimulus set comprising equal amounts of real and AI-generated videos (18 each). The AI clips were evenly distributed across the three generation methods using Google's Veo 3, Lightricks LTX Video, and Wan VACE. All videos were produced and standardized within the ComfyUI framework to ensure consistent quality and duration. 87 participants judged every clip in a binary forced-choice task ("real" vs. "AI-generated"). Participants correctly identified videos 60% of the time on average. Image-to-video clips were recognized most accurately (79%), followed by real footage (64%), outpainting (49%), and text-to-video (43%). Accuracy also varied by theme: film and historical scenes yielded higher detection rates than environmental clips, which were frequently mistaken for AI. Logistic regression confirmed significant effects of both technique and theme as well as their interaction (p < 0.001), indicating that detection success depends jointly on how the content was generated and what it depicts. Findings reveal a consistent bias toward assuming synthetic origins and highlight that perceptual realism in AI video is shaped more by context than by model type, underscoring the importance of media-literacy approaches and context-aware evaluation tools for navigating increasingly synthetic visual media.

cs.CV↗