【正文】 1) 187。 Over a short period of time 187。 A bad pose isn?t such a big deal 187。 Avoids discontinuities 187。 m(t) = a(t) m0(t) + (1a(t)) m1(t) Motion Signal Processing MOTION PLANNING IN REAL AND VIRTUAL ENVIRONMENTS FALL 2022 Blending for transition motion ? Okan et al. Siggraph ?02 Motion Signal Processing MOTION PLANNING IN REAL AND VIRTUAL ENVIRONMENTS FALL 2022 Time warping ? Dynamic Time Warping (DTW): Nonlinear signal matching procedure originating in field of speech recognition ? Finding the optimal sample correspondences between the two signals by puting the global minimum value of warping cost function Motion Signal Processing MOTION PLANNING IN REAL AND VIRTUAL ENVIRONMENTS FALL 2022 Time warping + interpolation Motion Signal Processing MOTION PLANNING IN REAL AND VIRTUAL ENVIRONMENTS FALL 2022 Displacement map ? Motion Warping Motion Signal Processing MOTION PLANNING IN REAL AND VIRTUAL ENVIRONMENTS FALL 2022 Displacement map ? Motion Warping ? Changing the shape of a signal locally through a displacement map while maintaining continuity and preserving the global shape of the signal. Motion Signal Processing MOTION PLANNING IN REAL AND VIRTUAL ENVIRONMENTS FALL 2022 Displacement map (td.) ? Mapping procedure Motion Signal Processing MOTION PLANNING IN REAL AND VIRTUAL ENVIRONMENTS FALL 2022 The Challenge ? High Quality, Expressive Motion 187。 Need motion capture (examples) ? Flexible, longrunning, controllable 187。 Need synthesis ? Synthesis from Examples! Motion Synthesis from Examples MOTION PLANNING IN REAL AND VIRTUAL ENVIRONMENTS FALL 2022 Idea: Put Clips Together ? New motions from pieces of old ones! ? Good news: 187。 Keeps the qualities of the original (with care) 187。 Can create long and novel “streams” (keep putting clips together) ? Challenges: 187。 How to connect clips? 187。 How to decide what clips to connect? Motion Synthesis from Examples MOTION PLANNING IN REAL AND VIRTUAL ENVIRONMENTS FALL 2022 Connecting clips: transition ? Transitions between motions can be hard ? Simple method: 187。 Blends between aligned motions 187。 Cleanup footskate artifacts 187。 When motions are similar ? Believe that blending will “work” ? Heuristic based on geometry ? Not perfect method ? Measure and use threshold ? Apply threshold conservatively Motion Synthesis from Examples MOTION PLANNING IN REAL AND VIRTUAL ENVIRONMENTS FALL 2022 Similarity Metric ? Factor out invariances and measure Motion Synthesis from Examples MOTION PLANNING IN REAL AND VIRTUAL ENVIRONMENTS FALL 2022 Motion Graphs (Kovar et al. ’02) ? Start with a database of motions, each with type and constraint information. ? Goal: add transitions at opportune points. ? Other Motion Graphlike projects elsewhere ? Differ in details. Motion Synthesis from Examples MOTION PLANNING IN REAL AND VIRTUAL ENVIRONMENTS FALL 2022 Motion Graphs ? Idea: automatically add transitions within a motion database ? Quality: restrict transitions ? Control: build walks that meet constraints Motion Synthesis from Examples MOTION PLANNING IN REAL AND VIRTUAL ENVIRONMENTS FALL 2022 Using motion graph ? Any walk on the graph is a valid motion ? Generate walks to meet goals 187。 Random walks (screen savers) 187。 Search to meet constraints ? An example: Motion Synthesis from Examples ?? Given a path ?? Find a motion that minimizes distance ?? Combinatorial optimization MOTION PLANNING IN REAL AND VIRTUAL ENVIRONMENTS FALL 2022 Why is this good? ? Search the graphs for motions ? Look ahead avoids getting stuck ? Cleanup motions as generated ? Plan “around” missing transitions ? Optimization gets close as possible Motion Synthesis from Examples Not OK for Interactive Apps! Need different tradeoff